The news had hit him like a physical blow. James had retreated to the gym, hoping to burn off the resentment twisting in his gut. The iron bar felt heavy and unwieldy in his hands. He slammed it down against the rack. Again. And again. Each repetition a release, but not enough. The sweat streamed down his face, blurring his vision. The announcer on the overhead speakers droned on, but James barely registered the words. He was focused on the burn, on the ache. He was consumed by this new revelation.

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