How LLMs Build Fictional Worlds: Setting and Narrative Space in AI-Generated Creative Storytelling
TL;DR
This paper compares 1,000 AI-generated stories per model in English and German with human-authored fiction from Project Gutenberg to find that human-authored texts predominantly employ "action space,"grounding narratives in embodied character-environment interaction, whereas LLMs systematically overproduce "perceived space,"emphasizing atmosphere and affect.
Abstract
In this paper, we analyze how Large Language Models (LLMs) employ worldbuilding strategies, focusing on setting as one measurable dimension of storyworld construction. We compare 1,000 AI-generated stories per model in English and German with human-authored fiction from Project Gutenberg. Building on prior work, we operationalize setting through five types of narrative space:"action","perceived,""visual,""descriptive"and"no space", identified using fine-tuned BERT classifiers for German and English. We generate narratives using GPT 4.1, LlaMA 3.3, Mistral 3.2, and Gemma 3 and compare their spatial distributions to a human-authored baseline. We find that human-authored texts predominantly employ"action space,"grounding narratives in embodied character-environment interaction, whereas LLMs systematically overproduce"perceived space,"emphasizing atmosphere and affect. This divergence remains stable across narrative time. Overall, our findings show that LLMs exhibit worldbuilding patterns that differ consistently from human-authored fiction in ways that are both model-specific and language-sensitive.
