He gripped the steering wheel so hard his knuckles were white. The highway, usually a source of calm, stretched before him like a menacing serpent. The radio's cheerful chatter grated on his nerves. He'd poured his heart into this application, painstakingly crafting the perfect resume, the ideal cover letter. Then, he'd found out that Emily, too, had put her hat in the ring.

He'd spent the last few weeks trying to ignore the subtle shift in their friendship. The way Emily had suddenly become quiet, thoughtful, or how she would go missing for hours on end. He'd initially shrugged it off, attributing it to the stress of the process. Now, the radio became almost unbearable. He gripped the steering wheel even harder, the world spinning.

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