"Acquired?" Mark repeated the word aloud, a question mark hanging in the air. The email’s subject line screamed the news, but the details remained a haze. He felt a throbbing ache behind his temples, and his vision seemed to narrow. He reached for his water bottle, his hand trembling slightly as he brought it to his lips.

He looked around the office, seeing his colleagues engrossed in their work, oblivious. He wanted to tell someone, to share the weight, but the words wouldn't come. He just sat there, frozen, the email’s impact slowly sinking in, stealing his breath.

He felt the sting of tears in his eyes. He quickly blinked them away, forcing himself to focus on the screen in front of him.

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