He’d always prided himself on his meticulous attention to detail. So the sloppy formatting of the reassignment email stung with a particular intensity. From the creative department to data entry. His hands were shaking so hard he could barely hold the mouse steady to minimize the tab. He had to physically pry his fingers away from the keyboard.

He stared at his reflection in the dark screen, his face a mask of disbelief and displeasure. He felt a cold dread creeping into his bones. His carefully constructed career, demolished in a single, poorly written email. He felt a deep, biting resentment, a knot of pure frustration. He gripped the edge of the desk, knuckles white, and just stared.

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