Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

Rain lashed against the windows, mirroring the tempest inside Amelia. She stared at the overflowing trash cans, a sight usually irritating but today, barely registering. Across the manicured lawn, Mrs. Gable’s house glowed with a warm, inviting light. Amelia, slumped on the sofa, had just learned her ex-boyfriend, Mark, was dating Mrs. Gable’s daughter. The same daughter who'd always sneered at Amelia’s second-hand car and thrift-store clothes.

Her stomach churned. The knowledge had hit her like a physical blow. She'd spent the last hour meticulously rearranging her spice rack, a futile attempt to impose order on the chaos that had erupted in her chest.

A car door slammed. Mrs. Gable, emerging from a sleek, silver convertible, glanced her way. A faint smile, quickly suppressed, played on the woman's lips. Amelia clenched her fists. It wasn't just Mark; it was the life he'd chosen. The life that felt utterly, painfully out of reach.

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