He slammed the laptop shut, the metallic clang echoing around the sterile apartment. His knuckles were white, his jaw clenched so tightly he could feel the muscles strain. He rose abruptly, pacing the small space, his steps agitated. The words of the editor, carefully chosen yet devastating, played on repeat in his mind.

He picked up a framed photograph of his grandmother, the one he'd dedicated the book to. Her smiling face, once a source of comfort, now seemed to observe him with a silent, judging gaze. He ran a hand through his hair, dislodging the strands and letting them fall to the floor.

He kicked a discarded shoe across the room, the impact a sharp crack that barely registered. He needed to be alone. He wanted the world to disappear. He craved the oblivion of a long, dark sleep.

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