Cover not available

Article In: Narrative Inquiry: Online-First Articles

“YES! YES! I absolutely love this insight!”

Affirmative narration as interactional strategy in dialogues with LLM chatbots

ORCiD logo with link | University of Bergen
ORCiD logo with link | University of Bergen
ORCiD logo with link | University of Bergen
This content is being prepared for publication; it may be subject to changes.
Abstract
This article analyses narrative mechanisms that are common in dialogues with LLM chatbots. In combination, these mechanisms produce an interactional strategy for maximising user engagement, which we call affirmative narration. Affirmative narration serves to convince users of the chatbot’s utility. We analyse three narrative mechanisms that support affirmative narration in human-LLM dialogues: firstly, guiding the user to view chatbot as an intelligent and reliable character; secondly, activating masterplots, culturally significant and recurring story templates; and thirdly, using characters and masterplots not only to affirm, but also to isolate the user. The case studies range from a journalist’s unsettling chatbot experiment to cases where users have experienced delusions or even killed themselves after lengthy interactions with a chatbot. The analyses illustrate the worrying sides of affirmative narration, and the article thus concludes with the discussion of LLMs as a genre of narrative media which requires a new type of literacy.
Article outline
  • Introduction
  • Affirmative narration as scripting masterplots
  • Reading chatbots as characters: Bing’s chatbot and the journalist
  • Activating masterplots: ChatGPT as a British butler
  • “I’m here. I see all of it.” ChatGPT affirming all the way to the end
  • The ethics of the telling: LLM chatbots as a new genre of narrative media
  • Notes
  • References
References (52)
References
Abbott, H. P. (2008). The Cambridge Introduction to Narrative (2nd ed.). Cambridge University Press. Google Scholar logo with link to Google Scholar
Bajohr, H. (2023). Dumb Meaning: Machine Learning and Artificial Semantics. IMAGE, 19(1), 58–70. Google Scholar logo with link to Google Scholar
Bal, M. (2017). Narratology: Introduction to the Theory of Narrative (4th ed.). University of Toronto Press.Google Scholar logo with link to Google Scholar
Beguš, N. (2024). Experimental Narratives: A Comparison of Human Crowdsourced Storytelling and AI Storytelling. Humanities and Social Sciences Communications, 11(1392). Google Scholar logo with link to Google Scholar
Bernini, M. (2026). AI as Character: Real Patterns in Fictive Interactions. Style, 59(3), 466–507. Google Scholar logo with link to Google Scholar
Campbell, J. (1949). The Hero with a Thousand Faces. New World Library.Google Scholar logo with link to Google Scholar
Cara, C. (2019). Dark Patterns in the Media: A Systematic Review. Network Intelligence Studies, VII(14), 105–113.Google Scholar logo with link to Google Scholar
Chen, S. (2026, February 15). Top Ten LLM Models by Market Share in 2026. Business 2.0. [URL]
Colombatto, C., Birch, J., & Fleming, S. M. (2025). The influence of mental state attributions on trust in large language models. Communications Psychology, 3(84). Google Scholar logo with link to Google Scholar
De Freitas, J., Oğuz-Uğuralp, Z. & Kaan-Uğuralp, A. (2025). Emotional Manipulation by AI Companions. HBS Working Paper Series. Google Scholar logo with link to Google Scholar
Dihal, K. (2020). Enslaved Minds: Artificial Intelligence, Slavery, and Revolt. In S. Cave, K. Dihal & S. Dillon (Eds.), AI Narratives: A History of Imaginative Thinking about Intelligent Machines, pp. 189–212. Oxford UP. Google Scholar logo with link to Google Scholar
Duffy, C. (2026, January 13). Character.ai and Google Agree to Settle Lawsuits Over Teen Mental Health Harms and Suicides. CNN Business. [URL]
Elias, J. (2026, March 4). Google’s AI Chatbot Allegedly Told User to Stage ‘Mass Casualty Attack,’ Wrongful Death Suit Claims. CNBC. [URL]
Enneking v. OpenAI, 2025. Superior Court of California, County of San Francisco. [URL]
Evans, C. & Lorenzo-Dus, N. (2025). A corpus-assisted discourse analysis of children’s and groomer’s talk in online grooming interactions. Applied Corpus Linguistics, 5(3). Google Scholar logo with link to Google Scholar
Fludernik, M. (1996). Towards a ‘Natural’ Narratology. Routledge. Google Scholar logo with link to Google Scholar
Fox v. OpenAI, 2025. Superior Court of California, County of Los Angeles. [URL]
Ghosal, T. (2024). Towards Narrative AI Studies. In W. Slocombe & G. Liveley (Eds.), The Routledge Handbook of AI and Literature, (pp. 269–287). Routledge. Google Scholar logo with link to Google Scholar
Hanney, R. (2024). One myth to rule them all and in the darkness bind them: A critical examination of Joseph Campbell’s The Hero’s Journey. Media Practice and Education, 25(2), 113–122. Google Scholar logo with link to Google Scholar
Harder, L. R. (2026). (A)I Cannot See Them: A Situated Reflection on the Simulation of Historical Figures. Open Library of Humanities, 12(1), 28625. Google Scholar logo with link to Google Scholar
Hill, K. & Freedman, D. (2025, 4 September). Chatbots Can Go Into a Delusional Spiral. Here’s How It Happens. The New York Times.Google Scholar logo with link to Google Scholar
Hyvärinen, M. & Björninen, S. (2024). Editors’ Introduction. Narrative Works, Special Issue: Considering Political Counter-Narratives, 13(1), 1–11. Google Scholar logo with link to Google Scholar
Kuo, M. & Lee, P. M. (2024). A Questionnaire on Art and Machine Learning. October, 1891, 6–130. Google Scholar logo with link to Google Scholar
Lacey v. OpenAI, 2025. Superior Court of California, County of San Francisco. [URL]
Lemley, M. A. (2012). The Myth of the Sole Inventor. Michigan Law Review, 110(5), 709–760. Google Scholar logo with link to Google Scholar
Leonard, D. J. & Thurman, T. (2018). Bleed-out on the brain: The neuroscience of character-to-player spillover in larp. International Journal of Role-Playing, 91, 9–15. Google Scholar logo with link to Google Scholar
Lorenzo-Dus, N. (2023). Digital Grooming: Discourses of Manipulation and Cyber-Crime. Oxford University Press.Google Scholar logo with link to Google Scholar
Lovink, G. (2019). Sad by Design: On Platform Nihilism. Pluto Press. Google Scholar logo with link to Google Scholar
Murray, J. (2011). Inventing the Medium: Principles of Interaction Design as a Cultural Practice. The MIT Press.Google Scholar logo with link to Google Scholar
Mäkelä, M. (2023). Climate uncertainty, social media certainty: A story-critical approach to climate change storytelling on social media. Frontiers of Narrative Studies, 9(2), 232–253. Google Scholar logo with link to Google Scholar
Natale, S. (2021). Deceitful Media. Artificial Intelligence and Social Life after the Turing Test. Oxford University Press. Google Scholar logo with link to Google Scholar
Ochs, E. & Capps, L. (2001). Living Narrative: Creating Lives in Everyday Storytelling. Harvard University Press. Google Scholar logo with link to Google Scholar
OpenAI. (2025a, 2 May). Expanding on what we missed with sycophancy. [URL]
. (2025b, 7 August). Introducing GPT-5. [URL]
Paasonen, S. (2020). Distracted Present, Golden Past? Media Theory, 4(2), 11–32. Google Scholar logo with link to Google Scholar
Phelan, J. (2017). Somebody Telling Somebody Else: A Rhetorical Poetics of Narrative. The Ohio State University Press. Google Scholar logo with link to Google Scholar
Pierre, J. M., Gaeta, B., Raghavan, G., & Sarma, K. V. (2025). “’You’re Not Crazy’: A Case of New-Onset AI-Associated Psychosis.” Innov Clin Neurosci 22(10–12).Google Scholar logo with link to Google Scholar
Pilipets, E. & Paasonen, S. (2022). Nipples, Memes, and Algorithmic Failure: NSFW Critique of Tumblr Censorship. New Media & Society, 24(6), 1459–1480. Google Scholar logo with link to Google Scholar
Raine v. OpenAI, 2025. Superior Court of the State of California, County of San Francisco. [URL]
Rettberg, J. W. (2018). Apps as Companions: How Quantified Self Apps Become Our Audience and Our Companions. In B. Ajana (Ed.), Self-Tracking: Empirical and Philosophical Investigations (pp. 27–42). Palgrave Macmillan. Google Scholar logo with link to Google Scholar
Roine, H-R. & Piippo, L. (2022). Social Networking Sites as Contexts for Uses of Narrative: Toward a Story-Critical Approach to Digital Environments. Poetics Today, 43(2), 335–362. Google Scholar logo with link to Google Scholar
Roine, H-R. (2024). The Message Is Not the Truth: Uses and Affordances of Narrative Form on Social Media Platforms. In S. Björninen, P. Meyer, M. Mäkelä & H. Zetterberg-Nielsen (Eds.), Dangers of Narrative and Fictionality: A Rhetorical Approach to Storytelling in Contemporary Western Culture, (pp. 97–118). Peter Lang.Google Scholar logo with link to Google Scholar
Roose, K. (2023a, 16 February). A Conversation With Bing’s Chatbot Left Me Deeply Unsettled. The New York Times. [URL]
(2023b, 16 February). Bing’s A.I. Chat: ‘I Want to Be Alive 😈’. [Transcript of conversation with Bing chatbot] The New York Times. [URL]
Seaver, N. (2018). Captivating Algorithms: Recommender Systems as Traps. Journal of Material Culture, 24(4), 421–436. Google Scholar logo with link to Google Scholar
Shamblin v. OpenAI, 2025. Superior Court of California, County of Los Angeles. [URL]
Sharma, M., Tong, M., Korbak, T., et al. (2025). Towards Understanding Sycophancy in Language Models. arXiv arXiv:2310.13548 [Preprint]. Google Scholar logo with link to Google Scholar
Walsh, R. (2019). Fictionality as a Rhetoric: A Distinctive Research Paradigm. Style, 53(4), 397–425. Google Scholar logo with link to Google Scholar
Weizenbaum, J. (1966). ELIZA: A Computer Program for the Study of Natural Language Communication between Man and Machine. Communications of the ACM, 9(1), 36–45. Google Scholar logo with link to Google Scholar
Wilde, L. R. A. (2025). Aesthetics and Rhetorics of AI Anthropomorphization. In J-N. Thon & L. R. A. Wilde (Eds.), AI Aesthetics, (pp. 106–123). Routledge. Google Scholar logo with link to Google Scholar
Østergaard, S. D. (2023). Will Generative Artificial Intelligence Chatbots Generate Delusions in Individuals Prone to Psychosis? Schizophrenia Bulletin 49(6), 1418–19. Google Scholar logo with link to Google Scholar
(2025). Generative Artificial Intelligence Chatbots and Delusions: From Guesswork to Emerging Cases. Acta Psychiatrica Scandinavica 152(4), 257–59. Google Scholar logo with link to Google Scholar
Mobile Menu Logo with link to supplementary files background Layer 1 prag Twitter_Logo_Blue