A cold knot formed in David's stomach when he saw the final score. 68%. He reread it, hoping the number would shift, morph into something higher. It didn’t. He gripped the test so hard, the paper threatened to tear. His palms were slick with sweat. He’d known the material, had aced every quiz. He'd even helped his classmates! Now, this.

He shoved the test into his backpack, the cheap nylon scraping against his nails. He felt a tremor start in his legs, a tremor of pure frustration. He wanted to scream. He wanted to tear the paper to shreds. He wanted to understand what he had done wrong. He walked in a daze to the student union, the familiar sounds of chatter and clinking cutlery now an irritating assault on his senses.

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