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 dust motes danced in the slivers of sunlight that pierced through the curtains, a silent, pointless ballet. Amelia had been staring at them for hours, a prisoner in her own house. The tasks she should have completed, the errands she should have run, remained undone. The weight of it all was overwhelming.

A real estate agent had contacted her recently, wanting to know if she was interested in selling. Her interest was minimal. Then the agent's email – a link to a podcast detailing a notorious unsolved case that had taken place within her walls. A missing person, a web of deceit. Her home had played a role in it. The story was gripping, but it didn't stir her. She simply sighed, another layer of the weight settling.

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