Rain hammered against the windowpane, mirroring the relentless drumming in Daniel's chest. He stared at the moving boxes stacked haphazardly in the living room, a monument to his failed freelancing career and the crushing weight of his parents' pitying gazes. He kicked one of the boxes, sending packing peanuts scattering across the worn rug. He really, really didn't want to unpack.

His mother bustled in, a steaming mug in her hand. β€œHere, dear. A nice cup of tea.” He snatched it, muttering a thank you that felt choked in his throat. The floral wallpaper seemed to close in on him, the scent of lavender and old books a suffocating blanket.

He retreated to his childhood bedroom, the posters of rock bands and faded sports teams mocking his present state. He collapsed onto the twin bed, the springs groaning in protest. He felt a profound sense of isolation, marooned on a tiny island of failure.

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