He watched the email notification, his heart thudding a frantic rhythm against his ribs. The subject line, “Job Application Update,” mocked him with its casual tone. Liam stared at the screen, the words blurring before his eyes. It was the same company, the same position, the same dreams that he and Emily had discussed over late-night coffees.

He’d known, of course, that she’d applied. They’d even talked about it, a casual, friendly conversation. Now, though, the air in his small apartment seemed heavy, thick with unspoken anxiety. He ran a hand through his hair, the familiar gesture failing to provide any solace.

He clicked the email. The message was brief, impersonal. He found himself pacing his living room, his steps rapid and uneven. The world tilted on its axis. He felt as though he was on a runaway train.

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