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).

Rain hammered against the attic window, mirroring the dull thrum in Eleanor's chest. She traced a finger across the dusty, cobweb-draped lid of the metal box, its inscription barely visible: "To the Future." Where had she even found this thing? A wave of weary confusion washed over her, making her eyes sting. She barely remembered her own name some days. She heaved the box open. Inside, a faded photograph of herself, beaming, caught her eye. Below it, a letter, addressed in her own childish scrawl, promised "adventures beyond your wildest dreams." The paper felt brittle between her fingers, and a profound sense of disconnect bloomed in her gut.

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