Sarah re-read the email, the words blurring. Her hands were shaking so hard she could barely hold the mouse. Her best friend, Emily, was relocating to Florida for her dream job. *Florida*. Sunshine and palm trees and… miles and miles away from her.

A knot formed in her stomach, a tight, painful lump. Tears pricked at her eyes, but she blinked them back, refusing to let them fall. She spun around in her desk chair, trying to distract herself by gazing out the window, but the scene was a blur, not the calm image she usually found.

She considered calling Emily, but the thought brought a new wave of sensation. Maybe later. She had to, just… adjust, first.

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