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 afternoon light filtered weakly through the attic window, casting long shadows across the dusty floor. Clara had been charged with clearing out her mother's possessions, a task she approached with a sense of utter detachment.

She opened a box labeled "My Precious." Inside, she found it: a treasure trove of school assignments. Essays, artwork, tests, all meticulously preserved. Her mother, the archivist of her own life, had held onto everything.

She picked up a handwritten poem, the words flowing across the page in a way that felt foreign, even alien. A strange, muted sense of apathy descended upon her. She sat down, her back against the wall, a wave of weariness stealing over her.

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