The aroma of old books and dried herbs filled the small, cluttered study. Clara picked her way through the maze of furniture, a box in hand. She felt no pressure to rush or finish quickly. She was simply there. She was exploring her mother’s old things. She found a leather-bound journal, a collection of pressed flowers, and finally, a folded sheet of paper tucked into a book. It was her mother's letter of resignation from a small law firm. Clara found a comfortable chair and settled in to read it.

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