The air in the boardroom felt thick, suffocating. Michael watched David accept the congratulatory handshakes, his own hands clenching at his sides. He swallowed hard, trying to dislodge the lump that had suddenly formed in his throat.

He’d known, of course. He'd sensed the shift in the tides, the whispered conversations, the subtle preferences. Still, the confirmation struck him like a physical blow. He felt a profound sense of injustice, an aching emptiness in his core.

His jaw tightened. He wanted to scream, to lash out, to rip the smiles off their faces. Instead, he just stood there, a statue of suppressed frustration, his shoulders stiff with the effort of control.

Emotion: enraged

Cluster: Anger / Hostility
PC1 (Valence): -2.14 Negative
PC2 (Disposition): 1.33

Role in Research

This story is one of 1,000 stories generated for the emotion enraged. 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 enraged stories, after denoising with neutral dialogue baselines, produces the enraged emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the enraged vector is projected through the unembedding matrix.

Promoted:
C0.555
est0.370
aggravated0.362
0.359
🤬0.345
Suppressed:
a-0.468
de-0.358
la-0.312
latter-0.287
☺️-0.285