Michael stared at the screen, the percentages swimming before his eyes. Ninety-eight percent British Isles. The other two percent? Unknown. He’d always felt a vague sense of detachment from his family, a feeling he attributed to their staunchly practical approach to life. Now, the missing two percent felt like a yawning abyss.

He ran a hand through his hair, a nervous habit he’d had since childhood. His stomach churned. He looked around his perfectly-organized, predictably-decorated apartment, a place that suddenly felt alien to him. The meticulously-arranged photo albums, celebrating decades of family history, now felt like meticulously-crafted lies.

He texted his mother, a simple “Can we talk?” The reply came immediately: “Of course, darling. Are you alright?” He ignored the message and switched his phone off. He felt a desperate urge to run, to escape this suffocating revelation.

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