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 clinking of silverware from the backyard barbecue next door, where the wealthy residents always held their parties, was an assault on Alice's senses. She stood at her kitchen window, watching the carefree revelry, a dull ache radiating outward from her chest. Mrs. Gable's parties always looked so glamorous, so perfect.

She picked at a half-eaten sandwich, the food tasteless in her mouth. She had wanted to start a business, to create, to make something of herself. But inertia held her in its grip, a silent, suffocating force.

She walked away from the window, back to the couch. Everything felt bland, muted, as if the colors had been leached from her world. She sat down, letting the weight of her apathy settle 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