The cafe buzzed, a chaotic symphony of espresso machines and chattering voices. Liam clutched his lukewarm latte, the ceramic feeling slick and foreign in his hand. He’d recognized her immediately – the cascade of auburn hair, the laugh that still tinkled like wind chimes. But when he’d approached, introducing himself, she’d blinked, a polite smile flickering across her face. “I’m sorry,” she’d said, her voice a smooth, unfamiliar sound, “I don’t think we’ve met.” He felt a sudden, inexplicable urge to flee, to disappear into the blur of the afternoon crowd. He sank back into the worn leather of the booth, the air suddenly thick and hard to breathe.

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