The letter arrived on a Tuesday, nestled among bills and junk mail. Emily, however, did not immediately open it. She held it, turning it over and over in her hands. The essay she'd submitted about losing her dog was a raw, personal piece. She knew her acceptance into the arts program hinged on the publication of her essay. She had already bought the materials for her first project, anticipating success. She set the letter down on the table, where the afternoon sun streamed in, casting a warm glow on the page. She decided to make herself a cup of tea, savoring the stillness.

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