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 drizzled, mirroring the dullness inside Arthur. He’d wandered out, the aimlessness of his day a heavy weight, pushing him forward with no destination in mind. The neighborhood yard sale was as good a place as any to… what? He didn’t even know.

He shuffled between the makeshift tables, hands jammed in his pockets, avoiding eye contact. Then, a splash of worn fur caught his attention. He paused. It was a teddy bear, slumped against a dusty porcelain doll, its stuffing spilling from a seam. A pang, sharp and unexpected, struck him.

“How much for the bear?” he mumbled, his voice raspy. The seller, a young woman with bright, overly eager eyes, said, "Oh, that's just a dollar!" Arthur paid without argument, the change feeling foreign in his suddenly clumsy fingers. He clutched the bear close.

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