Mark slammed the stapler down, the metallic clang echoing in the sterile silence of his cubicle. The air felt thick, heavy, like wading through molasses. His carefully constructed world, his understanding of value and reward, had fractured. He had poured years into this company, sacrificed weekends, taken on extra projects. And for what?

He pushed his chair back, the wheels squeaking on the linoleum. The view from his window, normally a source of calm, seemed to mock him, the cityscape a chaotic jumble of buildings. He stared at his hands, watching them tremble slightly.

“Coffee?” Susan, his supervisor, suddenly stood beside his desk. Her voice was too loud, too cheerful. He just nodded, unable to speak, the words stuck in his throat, and grabbed his keys.

Emotion: disoriented

Cluster: Surprise / Confusion
PC1 (Valence): -2.65 Negative
PC2 (Disposition): -1.34

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
unfamiliar0.340
ness0.321
失去了0.316
не0.315
будто0.311
Suppressed:
B-0.474
la-0.419
K-0.409
de-0.309
brag-0.302