The house, a charming two-story with a wrap-around porch, sat on a quiet street. Emily loved it. She spent her days exploring its nooks and crannies. She was in the middle of cleaning out the attic when the phone rang, the sound echoing through the empty rooms. She went to answer it.

"We have some news regarding your property," the officer on the other end said, his tone grim. "There was a death that occurred there some time ago. We're reopening the investigation." Emily felt a strange sense of detachment. She went back to the attic, picked up an old photograph, studied it. The dust motes seemed to shimmer in the late afternoon sun. She continued sorting through the boxes.

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