The first line hit him like a physical blow: "He loved the way she always left her shoes by the door." The author was his husband, Daniel. The woman was him. He read on, words blurring, the story unfolding with unnerving precision. He felt his face grow hot, his palms clammy. He was a character in a book, and he hadn't known.

He wandered into the bathroom, splashing cold water on his face. The reflection in the mirror seemed unfamiliar. The man staring back was not entirely himself. He grabbed his phone and texted Daniel, asking if he could come home early from his work trip.

When Daniel returned, he just stood there, speechless. Daniel, his face white, took a step back. "I... I can explain," he stammered.

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