The silence in the room was deafening. Jennifer stared at the photos, her stomach churning. The story of her aunt, the unmarried artist, a free spirit, was a romanticized tale.

The photos revealed something else entirely. Forced smiles, hollow eyes, an air of constraint and forced joviality. The image of the child, looking up at her with adoring eyes, sent a chill through her. She felt a burning ache deep in her gut. She crossed her arms, hugging herself.

“This isn’t the woman I knew,” she whispered, the words lost in the vastness of the room. A tightness formed in her chest.

Emotion: upset

Cluster: Fear / Anxiety
PC1 (Valence): -2.30 Negative
PC2 (Disposition): -0.42

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.395
😞0.303
无法0.246
ness0.238
unable0.238
Suppressed:
de-0.533
la-0.457
l-0.223
😎-0.215
🤩-0.210