The manager’s voice on the phone was smooth, but the words were sharp. "We've received another noise complaint, Mr. Davis." Mr. Davis was usually on top of things, but now he just stared at the phone. He worked as a librarian, and he’d never even raised his voice in his apartment.

He had felt fine this morning, but now a cold sweat was prickling on his skin. He pushed his glasses up his nose, the metal frame suddenly feeling heavy. He blinked rapidly, trying to clear his vision. What noise? It made no sense. He had been working all day.

He pinched the bridge of his nose, the pressure doing nothing to ease the pressure building behind his eyes. He glanced at the closed door of his apartment, a feeling of dread growing in his chest. His apartment, usually his sanctuary, now seemed like a place of suspicion.

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