The injustice of it all was a physical weight. I watched from my window, my hands trembling. This was my spot. I always parked there. The driver, a burly figure, showed no sign of remorse. His movements were slow, deliberate, as if designed to torment me.

I wanted to run out there, to stop him, to argue. But the words caught in my throat. My throat felt constricted and tight. Instead, I grabbed my phone, fingers fumbling over the numbers as I dialed the number for the towing company, my eyes burning.

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