The book launch. A room full of smiling faces. Cameras flashing. He stood on a stage, a forced smile plastered on his face. The author, a woman with piercing eyes, was giving a speech, praising the “courage” and “resilience” he'd shown. He wanted to scream. He wanted to run. Instead, he forced himself to nod, to accept the accolades, to play the part. His body felt disconnected, as if he were watching a movie about someone else. The noise was unbearable. He excused himself, feeling a surge of dizziness.

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