The steel doors slammed shut with a finality that made Sarah’s heart skip a beat. She’d been mid-sentence, recounting a weekend mishap. Now, all that remained was the metallic scent of stale air and the unnerving silence. Her colleague, Mark, cleared his throat, a nervous tic she’d noticed before, but never truly registered. He looked at the control panel, his brow furrowed.

“Well,” Mark said, his voice unusually high-pitched, “this isn't ideal.” Sarah just stared at him. She felt a strange detachment, like observing a scene unfold.

She patted her pockets, searching for her phone, then remembered she’d left it on her desk. A wave of disorientation washed over her. Three hours? Trapped? She pressed the button for the lobby again, then again, just in case. They didn't budge.

Mark started talking about the company’s new acquisition, his usual confident tone replaced with a hesitant tremor. She nodded, pretending to listen, but her focus was elsewhere, on the unsettling sensation in her chest, the prickly feeling crawling up her spine. The air felt heavy, oppressive, and she wanted out.

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