"Seriously?" Mark echoed, his voice barely a whisper. He reread the email, the words on the screen blurring slightly. He felt a pressure building behind his eyes, a tightness he usually only experienced during his migraines. This couldn't be right. He and Jessica had been hired at the same time, worked in the same department, and he'd always assumed they shared similar compensation. Apparently not.

He spun his chair around, staring out the window at the cityscape. The distant buildings seemed to mock him, their height a symbol of the success he'd been denied. He wanted to scream, to smash something.

His breath hitched as he pictured Jessica, who'd had the audacity to call him up the other night to discuss a project. "Oh, by the way, I got a raise..." she'd said. Her casual tone still rang in his ears. He stood up, knocking his chair over in the process. He needed to get out.

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