He stared at the email again. “Regretfully, The Golden Spoon will be closing its doors…” His jaw clenched. He felt a profound sense of disorientation, like being tossed in a rough sea. The restaurant, with its cozy atmosphere and the aroma of cinnamon rolls, was his sanctuary. It was where he went to think, to read, to escape.

He’d almost forgotten the meeting he was supposed to be in, lost in a sudden, sharp ache in his chest. He glanced at the clock; he would be late. Yet, he couldn’t bring himself to move. The image of the email flashed again, repeating itself on the screen.

He abruptly stood, pushing the chair backward with a screech, the sound grating. He didn’t know what he would do now. He felt a sudden, inexplicable sense of emptiness. He had to call Sarah, he thought – the one person who would understand.

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