John paced the living room, the glowing screen of his phone casting long shadows. He'd envisioned a fun ancestry project, a way to connect with a history he'd never truly considered. The reality, though, was a sucker punch. His “closest match” wasn’t a distant relative; it was a woman named Sarah, listed as “possible parent.” He stopped pacing, his legs refusing to support him any longer.

He slumped onto the sofa, the plush cushions suddenly feeling hard and unyielding. The photos on the website of Sarah and her family looked nothing like his own. His stomach churned. He picked up the ceramic mug on the coffee table, a gift from his father, and traced the rim with a shaking hand. He felt… adrift, like a tiny boat in a vast, unknowable ocean.

He wondered what to do. The silence in his apartment echoed the sudden hollowness inside him.

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