The bitter taste of coffee did nothing to soothe the ache in Thomas’s chest. He stared at the screen displaying the patented design of the automated dog-walking device. He felt a deep, twisting sadness. He had built his own, a more streamlined and efficient model, but it was too late. The feeling in his gut was a heavy sadness.

His apartment, usually filled with the happy barks of his golden retriever, was silent except for the rhythmic ticking of the grandfather clock. He ran a hand through his hair, leaving it rumpled. Thomas's appetite had vanished, and everything tasted bland. He considered selling his dog.

Emotion: heartbroken

Cluster: Sadness / Despair
PC1 (Valence): -2.60 Negative
PC2 (Disposition): -1.10

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.433
S0.385
😔0.359
haunting0.349
😢0.342
Suppressed:
de-0.503
la-0.455
B-0.352
🤓-0.332
!-0.299