The drive home was a blur. Michael gripped the steering wheel, knuckles white, his knuckles a white blur. The familiar route seemed strange and unfamiliar, each turn a potential wrong. The landscape morphed into an obstacle course of triggers, everything reminding him of the digital publication.

He barely registered the red lights, the other cars. His mind was a maelstrom of memories, all of which now belonged to the public. He felt a profound sense of unease, a constant churning in his stomach.

He pulled into his driveway, killed the engine, and just sat there, frozen in the seat.

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