Sarah wrapped her arms around herself, trying to ward off the chill that had settled deep within her bones. The words on the screen seemed to mock her, twisted and distorted in a way that left her feeling stripped and exposed.

She felt a dizzying emptiness in her stomach, a gaping void that threatened to consume her. She wandered into the bathroom, the cold tile a welcome relief against her flushed cheeks.

Looking in the mirror, she barely recognized herself. Her eyes were wide and vacant, her face a mask of disbelief and pain. She splashed cold water on her face, hoping to shock herself back to reality.

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