The elevator lights flickered, casting grotesque shadows across the small space. It was stuffy, the air thick with the smell of stale coffee from someone's forgotten travel mug. Michael tugged at his collar, feeling a sudden heat rising in his face. He glanced at Jessica, his coworker, who was staring blankly at the floor.

“This is… unusual,” he managed, his voice sounding hollow, even to himself. He wished he could make a joke, break the tension, but his brain felt like cotton wool. He touched his forehead, confirming the clamminess.

She blinked slowly, then began to press every button on the control panel, as if the sheer act of interaction would change the circumstances. He watched her, a knot forming in his stomach. The world, previously ordered, now felt tilted, unstable. He couldn't quite grasp what was going on.

The minutes crawled by, each one an eternity. He had to be calm. He had to think. But his thoughts were scattered, fragmented, unable to coalesce into anything coherent.

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