Emotion in Context: Human and AI Perspectives on the Affective Landscape of Severance

Emotion identification has long been a focus of interdisciplinary research spanning psychology, linguistics, and discourse analysis. Prior to the advent of artificial intelligence and large language models (LLMs), emotion recognition relied heavily on annotation and sentiment lexicons (e.g., Mohammad & Turney, 2013), often supported by sentiment analysis tools with limited sensitivity to contextual nuance. These traditional approaches, however, struggled with the complexity of emotional expression, particularly in multimodal or narrative-rich texts. Recent advances in natural language processing (NLP), particularly the development of LLMs, offer new possibilities for automating emotion detection with greater contextual awareness. This study investigates how emotions are represented and perceived in the television series Severance (Apple TV, 2022) through a multi-layered annotation framework based on Parrott’s hierarchical taxonomy of emotions. All nine episodes of season 1 were annotated scene by scene, producing four datasets: human text-only, human multimodal (video + audio + text), and two large-language-model (LLM) outputs. Comparative analyses assessed inter-annotator agreement, modality effects, and temporal and character-based emotion patterns. Results show that multimodal annotations yield a far richer and more nuanced emotional landscape than text alone, highlighting the decisive role of prosody, gesture, and facial expression in conveying affect. LLMs captured general emotional polarity but failed to reproduce fine-grained distinctions. Character profiles further reveal individualized affective strategies of repression, resistance, and awakening. The findings underscore the inherently multimodal nature of emotional meaning in audiovisual narrative.