“My life?” Sarah mumbled to herself, staring at the book. "Sarah Bloom: In Her Own Words..." Only, not really. Her stomach twisted into a painful knot.

She reached for a glass of water, her hand trembling so badly she nearly dropped it. She took a shaky sip, but it didn't help. The words swam before her eyes. The author, who she'd never met, had somehow crafted her entire narrative.

She felt a strange disconnect, like watching a movie of someone else's life. A bitter taste coated her tongue. The chair groaned as she pushed back from the table, and she began to pace.

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