The news hit Emily like a physical blow. Her investigative piece, the one that had taken her months to research and write, was printed under another name. A name she didn't know and certainly hadn't authorized. A cold sweat erupted on her skin as she scanned the newspaper, the words of her article now tainted. She felt a sickness churning in her stomach, a bitter taste rising in her throat.

Emily’s hands shook as she dialed her editor’s number. The ring tone grated on her nerves. She paced the length of her apartment, her agitation growing with each unanswered ring. She slammed the phone down in fury, the force of the action sending a shard of glass from the table across the floor.

She wouldn't let this slide. She would get to the bottom of this. This blatant theft.

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