The smell of stale coffee and old books filled Clara’s nostrils, a scent usually comforting, now repulsive. She sat across from the review board, her legs bouncing erratically under the table. Each question, each pointed inquiry, felt like a blow. The world around her warped and shifted.

She focused on the patterns in the floral wallpaper, trying to find a rhythm, a sense of grounding. Her mouth felt dry, her tongue thick and clumsy. She struggled to form coherent responses, her words stumbling and disjointed.

The faces of the committee members blurred, their expressions inscrutable. She felt adrift, lost in a sea of judgment, the familiar shore of her academic career receding rapidly. She wanted to scream.

Emotion: disoriented

Cluster: Surprise / Confusion
PC1 (Valence): -2.65 Negative
PC2 (Disposition): -1.34

Role in Research

This story is one of 1,000 stories generated for the emotion disoriented. 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 disoriented stories, after denoising with neutral dialogue baselines, produces the disoriented emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the disoriented vector is projected through the unembedding matrix.

Promoted:
unfamiliar0.340
ness0.321
失去了0.316
не0.315
будто0.311
Suppressed:
B-0.474
la-0.419
K-0.409
de-0.309
brag-0.302