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 world felt muted. Arthur shuffled through the supermarket, the fluorescent lights of the produce section casting a sickly glow. He reached for a bag of grapes, his hand heavy, his movements slow. He couldn't shake the feeling of being detached, like an actor waiting for the cue to enter a play he'd forgotten the lines to. He'd been drifting lately, just going through the motions. His friend, Ben, constantly spoke of his high-paying job in IT.

He ran into Ben earlier today, in fact, not in a modern office, but outside a fast-food restaurant. Ben was wearing a paper hat and handing out leaflets.

The air seemed to thicken around him.

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