The photograph, innocently nestled in a social media post, showed Michael in a clown suit. This came as a shock to Susan, who was under the impression that Michael was a world-class surgeon.

She felt a strange buzzing in her ears. Her hands started to shake. The carefully constructed façade, the precise language he used, the hushed tones when he described his “life-saving” work. She had adored him. Now it was all a cartoon.

Susan gripped the edge of her desk. She needed to take a walk, to clear her head. She stood up too fast and had to steady herself against the wall. She felt like she was trapped in a funhouse mirror, every reflection distorted and unbelievable.

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