He’d called it a “minor oversight.” A “clerical error.” Lies, all of it. Sarah’s jaw clenched so tightly she felt a muscle spasm. She had dedicated years to this research, sacrificing nights and weekends. Now, Professor Harding was presenting *her* findings as his own. She watched, motionless, as he projected the meticulously crafted slides she’d spent weeks agonizing over.

A strange buzzing filled her ears. The room felt suddenly too small, too warm. She wanted to scream, to disrupt the presentation, to tear the PowerPoint from the screen. Instead, she rose slowly, her legs feeling like lead weights. She could feel her face flush. Her hands felt clammy.

"Professor Harding," she managed, her voice barely a whisper. "Could you elaborate on the methods used to obtain these results?"

Emotion: furious

Cluster: Anger / Hostility
PC1 (Valence): -2.01 Negative
PC2 (Disposition): 1.23

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.461
0.376
🤬0.338
aggravated0.313
est0.304
Suppressed:
a-0.356
de-0.334
L-0.308
H-0.301
adventurous-0.256