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 in David’s soul. He hadn’t left the apartment in days, the takeout containers piling up like abandoned sentinels of a life unlived. His father's things, still scattered around, were a constant, nagging reminder of absence. He'd been sifting through them, a pointless exercise in nostalgia, when he found a faded file folder. Inside, a handwritten document: "Things to Do Before I Kick the Bucket." David stared at the first item: "Learn to play the ukulele." A bitter chuckle escaped him. His father, a man of routine and comfort, and yet… A sudden, unfamiliar itch sparked in his palms, a flicker of something beyond despair.

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