The cafe buzzed with Friday night chatter. Leo, hunched over his lukewarm coffee, felt a knot tighten in his stomach. The piano chords, a familiar progression, cut through the noise. It was his song. He knew every note, every chord change, every breath he took when he wrote it. He gripped the chipped mug so hard his knuckles whitened.

The singer's voice, a reedy soprano, warbled the melody. Leo buried his face in his hands. It sounded… wrong. The tempo was too fast, the phrasing clunky. He wanted to shout, to stop them, but his throat felt constricted. He just squeezed his eyes shut and willed the music to end.

Emotion: distressed

Cluster: Fear / Anxiety
PC1 (Valence): -2.39 Negative
PC2 (Disposition): -0.52

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.304
😞0.296
worse0.291
😖0.285
😰0.276
Suppressed:
de-0.457
la-0.349
:)-0.239
B-0.232
happy-0.229