The party was a cacophony of laughter, clinking glasses, and blaring music. He stood on the balcony, watching the revelry below, a detached observer. He felt an isolation like a physical weight, pressing down on him. Everyone seemed so energetic, so… normal.

He noticed a woman standing alone by the railing, gazing at the city lights. He recognized the subtle slump of her shoulders, the way she held her drink, a shield against the social storm. He knew what she was feeling, the ache of being different.

He approached her, offering a quiet, “Rough night?” She turned, surprised, then a slow smile blossomed on her face.

“You have no idea,” she replied, her voice soft. “Sometimes, it feels like I’m the only one.” He nodded, wordlessly acknowledging their shared reality.

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