"We think your speed would be better utilized on defense," the football coach announced, his voice devoid of any empathy. The quarterback, a position he'd worked tirelessly for since childhood, was being taken away from him. He felt his cheeks flush.

He balled his fists, the anger tightening every muscle in his body. He wanted to argue, to scream that he *was* a quarterback. He'd been born to lead the offense. Yet, he clenched his jaw shut, unable to speak, his throat constricting with the force of his emotion.

The other players, oblivious to his inner turmoil, chatted and joked around him. The injustice felt tangible, a physical weight pressing down on his chest. It felt unfair.

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