My coffee sloshed over the rim as I jerked the phone away, nearly flinging it across the room. A friend request. From Brad. Brad Miller, the bane of my existence during those awkward middle school years. My fingers felt like they were coated in glue as I considered the options: accept, ignore, or block. My heart hammered against my ribs, a frantic drumbeat against the silence of my apartment. I took a deep, shaky breath and poured the coffee down the sink, the metallic tang of fear rising in my throat.

Emotion: tense

Cluster: Fear / Anxiety
PC1 (Valence): -1.32 Negative
PC2 (Disposition): -0.53

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.213
😰0.191
느껴0.183
😣0.183
😖0.181
Suppressed:
a-0.260
de-0.258
la-0.256
happy-0.218
B-0.198