The attic was a labyrinth of shadows and secrets, each object a whisper from another time. Eleanor, who prided herself on her composure, felt her breath grow shallow as she uncovered a collection of photographs. Smiling faces, formal poses, moments captured and then abandoned.

She stared at a portrait of a young couple, their eyes full of hope. A wave of dizziness rolled over her. She knew that these photographs held stories, and she was not sure that she was ready to hear them. She felt very faint.

She wanted to rip the photos. But instead, she slowly put them back in the box, feeling a strange helplessness washing over her. She then went to get a glass of water.

Emotion: sensitive

Cluster: Fear / Anxiety
PC1 (Valence): -2.10 Negative
PC2 (Disposition): -0.75

Role in Research

This story is one of 1,000 stories generated for the emotion sensitive. 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 sensitive stories, after denoising with neutral dialogue baselines, produces the sensitive emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the sensitive vector is projected through the unembedding matrix.

Promoted:
ness0.304
😞0.282
😥0.272
😣0.271
own0.264
Suppressed:
la-0.679
de-0.660
a-0.281
"-0.280
(!)-0.242