The opening night was a disaster. She'd found out about it through a friend, a frantic text message that had sent a chill through her. Now, standing here, amidst the chattering crowds and the clinking glasses, she felt a profound sense of violation. Her artwork, her most private thoughts and feelings, were on public display, sold for profit.

She could barely bring herself to look at the canvases, the vibrant colors now seeming to mock her. The air tasted metallic, and her breath hitched in her chest. She excused herself, seeking refuge in the gallery's restroom.

Staring at her reflection in the mirror, she looked like a stranger, cheeks flushed, eyes wide with a suppressed fury. Hot tears welled up, blurring the image.

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