Martin slammed his fist on the table, rattling the coffee cups. He’d discovered the truth about the author he adored, the one whose style he’d imitated, whose words he’d memorized. The article displayed side-by-side comparisons of the man's latest work with stories from unknown authors and the similarities were impossible to ignore. A vein in his forehead throbbed.

He stood up, his chair scraping against the floor. He needed to get away, to clear his head, to *do* something. He grabbed his coat, then dropped it back on the chair.

He started to laugh, a harsh, brittle sound that echoed in the empty apartment.

Then, he sat back down and began writing a scathing review of the book.

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