The knot in his stomach tightened with each passing second. He reread the request, the words burning into his brain. He wanted to shout, to rail, to make them understand. But the words stuck in his throat.

He slammed his fist on the desk, the impact echoing in the silent office. He felt his face flush, a heat spreading across his neck. He needed to get out, to walk, to think.

He gritted his teeth as the newbie, a guy named David, started asking questions. Every question seemed like a personal insult, a confirmation of his imminent irrelevance. His responses were terse and devoid of emotion.

Emotion: outraged

Cluster: Anger / Hostility
PC1 (Valence): -1.96 Negative
PC2 (Disposition): 1.32

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.467
0.334
🤬0.327
aggravated0.323
0.312
Suppressed:
H-0.315
☺️-0.286
optimistic-0.278
adventurous-0.262
मुस्कुरा-0.260