The familiar scent of cinnamon and brewing coffee filled the air, but something else did too: a low, murmuring voice. Daniel paused in the doorway to the kitchen, a sense of foreboding settling over him. He found Emily standing at the stove, her back to him, humming. The tune was new to him, the words even more so.

He cleared his throat. Emily flinched, then whirled around, a cookbook clutched in her hands. The book was open to a page in Farsi.

“Morning,” he said, forcing a casual tone. His palms began to sweat.

"Good morning, honey," she replied, her voice a little too airy. Daniel felt a lightness in his chest, an unsettling sensation like he was being left behind. He couldn’t quite place 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