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 bright lights of the bakery glared down on Maya. The review, a scathing criticism of her signature croissants, was taped to the fridge. "Dry," the critic had written. "Lacking in flavor." She picked up a rolling pin, the weight of it heavy in her hands. She usually loved the feel of the dough, the way it yielded under pressure. Today, the task felt like a burden.

She started to work, the motions rote and without energy. She felt empty, devoid of inspiration. Every step felt like a chore. The air in the bakery was thick with the scent of flour and butter, but it no longer comforted her. It felt like an illusion.

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