The office felt stifling. The air conditioning hummed, a monotonous drone that did little to cool the internal fever she was experiencing. He swiveled in his chair, staring out at the grey cityscape, trying to focus on anything other than the digital excavation of his adolescence. The words. The words, the words, the words.

He slammed his fist lightly on the desk, the sudden movement startling him. His heart was hammering against his ribs. He felt a strange tingling in his fingers. He imagined all his colleagues, all his friends, now reading about the embarrassing poems he'd written.

His phone buzzed. He ignored it.

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