The tiny, handwritten notes scattered across the desk were like tiny daggers. Adrian had always scoffed at Lucia’s Mandarin lessons, dismissing them as a ‘waste of time’. Now, here they were, evidence of clandestine study. Phrases, characters, all meticulously penned.

He felt a tightness in his chest, a sensation akin to suffocation. The air in the room seemed to have become impossibly thin. He paced the small space, his steps agitated and erratic.

He found her in the garden, watering the roses. He had to clench his teeth to prevent the words from bursting out, his voice shaking when he finally spoke: "Why?"

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