The chipped mug warmed her hands, but couldn’t chase the chill that had settled in her bones. She’d been enjoying a rare moment of peace, reading, when the familiar ringtone shattered the quiet. Across the room, Michael had practically leaped for his phone.

The call was short, hushed. He had turned his back to her, shielding the screen. When he hung up, his face was carefully blank. She bit back the question that clawed at her throat. He'd been distant, unavailable, for weeks.

She closed her book, the words on the page blurring into an unintelligible mess. She felt a profound loneliness, a desolate landscape stretching out before her. She didn’t know which was worse: the not knowing or the knowing.

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