The bustling atmosphere of the market calmed Beatrice. Finding a used bookstore tucked away in the corner, she knew her hunt was over. She had a fondness for the old, finding comfort in the quiet. She decided upon a book by Virginia Woolf, and went to the nearest available reading area. A library card, belonging to a name she didn’t recognize, slipped from between the pages. A detailed record of books read. She took the time to read through the titles, imagining the life of the cardholder.

Emotion: patient

Cluster: Passivity
PC1 (Valence): 2.71 Positive
PC2 (Disposition): 0.40

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
rest0.467
eventually0.415
leisurely0.369
慢慢0.357
a0.355
Suppressed:
无法-0.432
even-0.428
인해-0.421
無法-0.415
😣-0.391