Her palms were clammy. She found herself wringing her hands as her daughter, Chloe, explained her conversion to Rastafarianism. The vibrant colors in Chloe’s new wardrobe clashed with the muted tones of the living room, a visual representation of their growing distance.

A sudden tremor ran through her, shaking her entire frame. She felt a profound sadness, a sense of having failed. She thought of their future, the holidays and family gatherings. How would she cope?

She retreated to the kitchen, seeking solace in familiar tasks. She poured herself a cup of tea, the steam rising, a thin wisp of smoke, carrying away her hopes. She rested her forehead against the cold countertop, the tile a cold comfort.

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