The weight room smelled like iron and disappointment. Mark dropped the barbell with a deafening clang, the sound reverberating through his skull. He didn't bother to rerack it. His vision swam. Coach Harrison's justification for cutting him, about the team needing "more versatility," felt like a cruel joke.

He slammed his hands on the bench, the impact jarring his teeth. The urge to break something simmered beneath his skin, a burning tide threatening to overwhelm him. He wanted to go out onto the field and tear the grass up, root and all. He wanted to destroy something. Anything.

His breath came in ragged gasps. He wiped the sweat from his brow, smearing the grime across his forehead.

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