Clara felt a cold dread wash over her as she read the manuscript. Her husband, Ben, had written a book detailing their relationship, thinly veiled as a work of fiction. In the pages, she was a frantic, emotionally needy person, almost comically so. A wave of shame hit her.

She sat on the sofa, clutching the laptop to her chest. She couldn't cry. Tears wouldn't come. Instead, she felt a numb stillness, a void where her emotions should be.

She slowly placed the laptop on the coffee table. She needed to get out, to breathe. The air inside the house felt thick, suffocating.

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