The damp chill of the basement seeped into Eleanor's bones, but she barely noticed. A small, round table was her domain, piled high with albums and boxes. She had chosen to spend the afternoon down here, sifting through the legacy of her great-aunt.

Everyone remembered Aunt Clara as a prim, proper schoolteacher, the epitome of Victorian virtue. Then, she picked up a photo, a candid shot of Clara in her twenties, laughing hysterically at something – a man, perhaps? The image was a startling contrast to the demure woman Eleanor had known from infrequent visits.

Eleanor took her time, turning the picture over, letting her mind wander. The story would slowly unearth itself. She had all the time in the world.

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