The vibrant colors of the art gallery mocked her, the lively chatter of the other guests a painful soundtrack to her misery. The announcement email. The job. The triumph. It was all swirling around in her head. Leo. Of course, it was Leo.

She took a large gulp of the champagne, the bubbles stinging her throat, but failing to distract her from the ache inside. She spotted him across the room, laughing with the gallery owner. His easy success. Her hard work.

She excused herself and headed for the restroom, the elegant surroundings feeling suddenly sterile. She splashed cold water on her face, trying to wash away the feeling. Looking into the mirror, she saw a stranger staring back.

Emotion: upset

Cluster: Fear / Anxiety
PC1 (Valence): -2.30 Negative
PC2 (Disposition): -0.42

Role in Research

This story is one of 1,000 stories generated for the emotion upset. 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 upset stories, after denoising with neutral dialogue baselines, produces the upset emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the upset vector is projected through the unembedding matrix.

Promoted:
S0.395
😞0.303
无法0.246
ness0.238
unable0.238
Suppressed:
de-0.533
la-0.457
l-0.223
😎-0.215
🤩-0.210