The fluorescent lights of the break room hummed, a jarring counterpoint to the silence that had fallen over the office. Sarah stared at the email, the words blurring despite her efforts to focus. *Acquired by StellarTech*. Her coffee sat untouched, the lukewarm liquid now looking utterly unappealing. She vaguely remembered making it, five minutes ago, before the world seemed to shift.

Her hands felt clammy, and she ran them across her jeans, trying to dry them. The scent of stale donuts, usually comforting, now turned her stomach. She pictured Mr. Henderson, the CEO, his usual booming laughter suddenly echoing as a forced performance. He hadn’t mentioned anything during their last performance review.

She needed air. Without thinking, she pushed open the fire escape door and stepped onto the metal landing, the city’s distant rumble a vague, disconnected noise. The wind whipped her hair across her face, but she barely registered it. This couldn’t be right.

Emotion: bewildered

Cluster: Surprise / Confusion
PC1 (Valence): -1.87 Negative
PC2 (Disposition): -0.48

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
будто0.300
ness0.255
像是0.241
worse0.231
Worse0.219
Suppressed:
la-0.373
மகி-0.229
happy-0.226
ecstatic-0.226
K-0.219