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).

Mr. Davies felt as though he were wading through thick mud. The noise of the school was a cacophony, his own life a slow, grinding machine. The work felt heavy, the rewards nonexistent.

An email arrived, a digital message from a former student, Chloe. He usually ignored these, but this one caught his eye. It contained a digital gift, a music track.

He listened to it, and he found himself tearing up. The song was a moving piece, something from Chloe herself. In the subject line of the email, she wrote: "Thank you for the inspiration, teacher". He felt a pang of surprise, of a connection that he thought was long gone.

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