John sat frozen in his chair, staring at the email, its stark words glaring back at him. It was a formal acknowledgment of the situation, a sentence that felt like a sentence of his own.

He slammed his laptop shut, the sound echoing in the silent office. He needed a moment, a second to breathe, but his lungs felt constricted. He felt suddenly ill. The image of the other candidate, the one he had always considered a friend, now an adversary, flashed through his mind.

He couldn't sit still. He paced his small office, unable to find a stable surface. Every step felt unsteady, every breath felt shallow.

Emotion: shaken

Cluster: Fear / Anxiety
PC1 (Valence): -2.72 Negative
PC2 (Disposition): -0.86

Role in Research

This story is one of 1,000 stories generated for the emotion shaken. 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 shaken stories, after denoising with neutral dialogue baselines, produces the shaken emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the shaken vector is projected through the unembedding matrix.

Promoted:
S0.351
unable0.269
focus0.266
😞0.258
다시0.257
Suppressed:
de-0.769
la-0.579
a-0.375
happy-0.292
"-0.290