The email sat in Eleanor’s inbox, the subject line a damning verdict: “Possible Plagiarism.” Her hand, usually steady, trembled as she clicked. Inside, a side-by-side comparison of her short story, “The Gilded Cage,” and a passage from Alistair Finch’s latest bestseller, “Shadows of Remembrance.” Her jaw clenched. Finch, the literary titan she’d worshipped since childhood, had seemingly stolen her words, her imagery, her very soul.

She slammed her laptop shut, the sound echoing in her otherwise silent apartment. The air felt thick, suffocating. She paced the length of her living room, her steps quick, erratic. The walls, once comforting, now seemed to press in on her.

"He wouldn't," she muttered, the denial a weak shield against the truth. It was a flimsy defense, and it shattered as another, more detailed comparison arrived, this time with a lawyer's letter attached.

She spent the entire evening, the night, and a good part of the next day in a fury of activity. Drafting a response to the letter, searching for Finch’s contact information, and finally screaming at her cat.

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