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 attic air hung thick and heavy, dust motes dancing in the single shaft of sunlight piercing the gloom. Sarah, tracing a finger across the spine of a forgotten photo album, felt a profound inertia. Time seemed to have stalled. It had been six months since her mother's passing, and the days bled into each other, a monotonous watercolor wash of grey. The album clattered back onto the shelf. Behind it, tucked inside a chipped ceramic vase, she found a small, leather-bound notebook. Her mother's handwriting, spidery and familiar, filled the first page: "Bucket List." Sarah sank to the floor, the notebook clutched in her hands. The first entry: "See the Northern Lights." A hollow ache settled in her chest.

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