"You're kidding me," muttered Chloe under her breath. She'd just seen the official salary document left on the printer by the new recruit. She leaned closer, double-checking the figures. The numbers swam before her eyes. The difference was significant.

Her breath hitched. She walked back to her desk and sat down heavily, the chair creaking under her weight. She felt a growing tightness in her chest, a pressure building like a held-back sob. She looked at her carefully organized desk, the picture of her kids, and felt a rush of something akin to panic. What was she doing wrong?

She reached for her phone, intending to text her friend, but instead, just stared at the screen, the words refusing to form. She felt utterly lost.

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