David’s hands trembled as he held his phone, the article on the screen. He didn’t understand. His essay on his love for his grandmother was now available online, as an exemplary piece. He felt a throbbing pulse in his temples. He read the introduction. It framed his personal experience as a model for aspiring students, a blueprint for future success.

He felt the blood drain from his face. A wave of nausea swept over him. He had written the essay for a very specific audience, and for a very specific reason. Now it was plastered on the internet. He stared blankly at the words, unable to process them. They felt like someone else's.

He abruptly stood up and began pacing the small apartment. He didn’t know what to do. The world suddenly felt sharp and unforgiving. He grabbed a nearby water bottle and downed the entire contents in one go.

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