Emotion is Not Just a Label: Latent Emotional Factors in LLM Processing

ArXi:2603.09205v1 Announce Type: cross Large language models are routinely deployed on text that varies widely in emotional tone, yet their reasoning behavior is typically evaluated without accounting for emotion as a source of representational variation. Prior work has largely treated emotion as a prediction target, for example in sentiment analysis or emotion classification. In contrast, we study emotion as a latent factor that shapes how models attend to and reason over text.