The scent of stale coffee and hot dogs from the nearby food truck only intensified Marcus’s building rage. He'd found the bear. Theodore. He recognized the faded patch on its ear, the missing button eye. This was unacceptable. This was beyond the pale. The woman was cheerfully chatting about how old it was and how much she would like to get for it. "That's not even close to being worth it!" he barked, his voice rough. He was ready to walk away, to leave it there, but the thought of it being bought by some child, who would never know its history, was unbearable.

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