Do AI stories align with the laws of the story economy?

Abstract

The article situates LLM-generated narratives within the twenty-first-century story economy by asking how they rework the storytelling patterns shaped by social media, algorithmic optimization, and the pursuit of the “compelling story.” Previous research has shown that stories gaining traction on social media conform to the experiential narrative prototype outlined by sociolinguistics and cognitive narratology, and that this prototype overlaps with the universalist conceptions of narrative promoted by storytelling manuals and consultancy practices since the 1990s. We examine whether this prototype, which privileges personal transformation, survives in the training materials of LLMs and persists through alignment processes. We analyze 60 stories generated through minimal prompting using DeepSeek, ChatGPT, Copilot, and Grok. The results point towards the emergence of a new narrative prototype that invites us to reconsider narrative capital as it was understood in the Web 2.0 era with social media as its main narrative environment.