The email landed with a thud, a digital brick in Sarah’s inbox. “Company Acquisition – Important Announcement.” Her coffee went cold in her hand. A knot tightened in her stomach, a familiar unwelcome guest. She scrolled through the document, the words blurring before her eyes. The familiar logo, the place where she'd spent the last seven years, was now… different.

Her breath hitched. She swiveled her chair away from her desk, staring out at the cityscape. The gleam of the morning sun felt mocking. The sale felt personal. She'd poured her heart into this job, into this team. Now, what?

She slammed the laptop shut, the metallic clang echoing in the otherwise silent office. She needed air. Needed to not think.

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