The train rumbled along the tracks, the repetitive clatter a familiar soundtrack to Leo's life. He gazed out the window, watching the landscape blur. He knew this trip wouldn't be the same, ever. He'd find her later, as always.

He’d known for weeks. Sarah's new job, her dream, was in Seattle. He'd sat across from her at that café, listening to her excited descriptions. He kept his posture relaxed, his hands still. He focused on the details of her face, the way her eyes lit up when she spoke of the mountains.

He picked up a book, flipping through the pages. The words offered a quiet comfort, a gentle distraction from the ache that was not in his shoulders.

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