The interview felt like a funhouse mirror. Sarah kept catching her reflection in the polished table, and each time, her smile seemed…off. Across from her, Mark, her best friend, tapped his pen against the notepad. He looked calm, collected, the way he always did when facing pressure. She, on the other hand, felt a frantic fluttering in her chest, a hummingbird trapped in her ribs.

She’d rehearsed all the answers, the elevator pitch, the weaknesses, and strengths. But now, under the assessing gaze of the hiring manager, the words felt foreign, clumsy. She stumbled over a simple explanation of her previous role, her tongue suddenly too thick for her mouth.

Later, walking out, the sun felt impossibly bright, the city noise overwhelming. Mark clapped her on the back, said something about “giving it her best shot.” She just nodded, her throat constricted, unable to muster more than a strained smile. It wasn't the rejection she was anticipating, it was the disconnect.

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