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).

The chipped mug warmed Amelia’s hands, but did little to soothe the hollowness in her chest. She stared out the rain-streaked window, watching the city blur. Another grey day, mirroring the mood that had settled upon her like a damp shroud. Bills piled up on the kitchen counter, each one a tiny weight, adding to the burden she felt incapable of carrying. A sudden knock at the door startled her, making her jump. It was a courier, holding a thick envelope. Inside, a letter and a photograph. The letter explained everything: a father she never knew, a woman he'd been with, a half-sister. The photo showed a girl with her father’s eyes, a smile that seemed both familiar and utterly alien. Amelia felt the air whoosh from her lungs.

Emotion: listless

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.03 Negative
PC2 (Disposition): -1.07

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
’0.325
давно0.280
unremarkable0.270
lately0.266
either0.266
Suppressed:
B-0.460
P-0.331
l-0.312
C-0.292
👏-0.273