From his vantage point, the city seemed to shimmer, the lights of the buildings blurring into a hazy mess. Daniel stood at the window, the rejection letter clutched in his hand. The words, so clinical and detached, were a direct affront. It was as if they hadn’t even read his work, his soul spilled out on the page. His fingers tightened around the paper until his knuckles were white. He needed to be alone. He needed to walk, to get away from the oppressive feeling of disappointment, to escape the confines of his apartment.

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