The chipped mug of coffee felt heavy in Clara's hand. She’d been scrolling through the online therapist directory, feeling a flicker of hope. She needed someone, someone safe. But as she clicked on "Dr. Thomas Miller's" profile, a picture blinked up at her. The name was familiar. The face even more so. The guy who used to steal her lunch money and call her names. The guy she'd actively avoided for twenty years.

Her head spun. She slammed the laptop shut. What kind of cruel joke was this? She wanted to laugh, but she couldn’t. A nervous energy surged through her limbs, making her pace back and forth across her apartment. She felt like she'd been physically punched in the gut.

She couldn’t do it. Could she?

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