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 morning was overcast, mirroring the mood that clung to Emily like a second skin. She sat at the kitchen table, pushing a forkful of scrambled eggs around her plate. The food tasted like ash.

A knock echoed, and the man next door was at her door. He spoke quickly, pointing to the dying elm. "It's a hazard," he said, his words clipped. "I have to take it down, it's a matter of safety."

She barely registered his words. The thought of the massive tree, the familiar presence in the landscape, disappearing, caused a dull ache in her chest. She mumbled some form of agreement, then turned back to her plate, suddenly unable to swallow.

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