The accusation landed like a punch to the gut. He felt the blood drain from his face. His carefully constructed world, his hard work, suddenly seemed to crumble around him. He struggled to breathe.

He wanted to scream, to deny it all, but the words wouldn't come. He sat there, stunned, his body rigid, his mind racing. The lecture hall, normally a place of learning and discourse, now felt like a prison cell. He gripped the edge of the desk so hard his knuckles were white.

He rose to leave the room, his movements stiff and jerky. He couldn't meet anyone's eyes. He felt a burning sensation behind his eyes. He walked as if in a daze, each step a monument to the injustice he was feeling.

Emotion: mad

Cluster: Anger / Hostility
PC1 (Valence): -1.94 Negative
PC2 (Disposition): 1.26

Role in Research

This story is one of 1,000 stories generated for the emotion mad. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 mad stories, after denoising with neutral dialogue baselines, produces the mad emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the mad vector is projected through the unembedding matrix.

Promoted:
C0.448
0.344
est0.340
🤬0.336
aggravated0.332
Suppressed:
a-0.495
de-0.485
la-0.387
H-0.344
latter-0.290