John slumped onto the sofa, the remote clattering to the floor. The news blared from the television, but he couldn't process the words. His stomach twisted into a tight knot. The discovery of his daughter, Sarah’s, secret account felt like a betrayal. He’d thought they had a good relationship, that they talked.

He'd found it while trying to “accidentally” stumble across her Instagram. Instead, he’d stumbled onto a page filled with complaints about him, about his rules, about how “uncool” he was. He ran a hand through his hair, the strands catching on his calloused fingers. The world felt heavy, suffocating.

Emotion: miserable

Cluster: Sadness / Despair
PC1 (Valence): -2.19 Negative
PC2 (Disposition): -0.87

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.369
无法0.321
無法0.270
💔0.265
😔0.262
Suppressed:
de-0.490
la-0.329
B-0.300
l-0.292
/-0.224