Sarah slammed the laptop shut, the metallic clang echoing in the otherwise silent kitchen. Her hands trembled as she rose from the chair, the blood rushing in her ears. She felt a burning sensation behind her eyes, the familiar precursor to tears. David’s secret… tucked away, growing, while she was meticulously budgeting every single grocery bill. She paced the length of the galley kitchen, her breath coming in shallow, ragged gasps. He had been so insistent on "being frugal" and "cutting back." Now, she had proof.

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