The clinking of the ice in his glass was the only sound in the otherwise quiet apartment. Michael took a large gulp of the watered-down whiskey, his throat suddenly dry. The air seemed thin, as if he was struggling to breathe. Across the room, Ben was cradling a small, fluffy kitten, already cooing at it. A cat. Michael’s stomach clenched.

He'd spent years perfecting his apartment. The smooth surfaces, the clean lines, the absence of any unnecessary clutter had always brought him a sense of calm. The thought of a cat scratching furniture, shedding fur, and generally wreaking havoc on his well-ordered world sent a shiver down his spine. He imagined the cat's claws on his skin.

He gripped the glass so hard his knuckles turned white. He wanted to scream. He forced himself to take another sip, trying to regain his equilibrium.

"Are you sure it's house-trained?" he asked, his voice strained.

Emotion: anxious

Cluster: Fear / Anxiety
PC1 (Valence): -1.99 Negative
PC2 (Disposition): -0.24

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.315
😖0.302
worse0.297
😰0.285
own0.267
Suppressed:
la-0.441
a-0.382
de-0.365
"-0.256
happy-0.256