He found himself pacing the cramped hallway backstage, listening to the echoing sound of his song from the auditorium. They were performing it at a charity benefit, a gesture of "respect" for his work. Respect? It felt like mockery. His face was flushed, hot.

His fists were balled so tightly his nails dug crescents into his palms. The song was stripped bare, cleaned up, rendered innocuous. His song, his words, had been weaponized against him.

He pictured the smug smile of the performer, the syrupy pleasantries. He wanted to confront them, tear them limb from limb, expose them for the fraud they were. Instead he clenched his teeth, feeling the pressure behind his eyes.

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