"Just go," David had shouted as they were leaving. The words echoed in her ears. He had been like that. She wandered aimlessly, wanting to disappear. She turned a corner and spotted a yard sale overflowing with junk. Something drew her closer. A faded bear, tucked in a box of old stuffed animals. She knew the eyes.

Her shoulders slumped. She asked for a price, her voice flat. The woman behind the table didn’t seem to notice her.

Back in her car, she clutched the bear, the familiar scent of lavender from her childhood. She drove towards the coast, watching the waves crash against the shore. She cried, silently, her breath catching in her throat.

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