“Damn it,” I muttered, staring at the screen. It was Jessica. Jessica Reynolds. The name alone brought back a flood of unwanted memories. I hadn't seen or spoken to her since high school. My hands started to sweat.

I got up from my desk, pacing back and forth in my small apartment. I felt claustrophobic, trapped. I ran my hands through my hair, feeling the franticness radiating in my body. Each step felt heavy and deliberate.

I grabbed the remote and turned on the TV, flipping through the channels without actually seeing anything. My mind kept returning to that friend request. It was like a looming shadow, filling the room with a weight I couldn’t shake.

Emotion: uneasy

Cluster: Fear / Anxiety
PC1 (Valence): -1.80 Negative
PC2 (Disposition): -0.43

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😰0.240
😖0.231
😣0.231
느껴0.226
worse0.222
Suppressed:
de-0.474
la-0.465
happy-0.261
a-0.255
ecstatic-0.228