Her phone pinged during a particularly tense scene in a movie. Mr. Garcia, her Spanish teacher, had liked her latest Instagram post. It was a picture of her at a concert, captioned with a very candid, and somewhat embarrassing, observation about the opening band. She felt like she'd been caught doing something wrong.

She paused the movie, the silence suddenly deafening. Her palms felt clammy. She took a deep breath, trying to calm her racing heart. She wanted to look at her phone, but she found herself resisting the urge. She needed to think. She needed to understand. She was completely unsettled.

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