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 windowpane, mirroring the dull thrum in Eleanor's chest. She stared at the blurry cityscape, a tapestry of shimmering grey and orange, and felt utterly disconnected. The aroma of stale coffee hung in the air, a familiar scent that usually sparked a small, comforting ritual. Today, it simply… was. Her phone buzzed; a notification from her sister. She ignored it. This morning, even the mundane act of checking messages felt like traversing an endless desert.

A package arrived, a heavy rectangular box bearing her name. With a sigh that felt like it originated from the core of her being, she dragged it to the table. Inside, nestled amongst packing peanuts, was a book. The cover, a stark black, bore her name, and a title that made her stomach clench: "Eleanor Vance: A Life Unfolding."

She ripped the shrink wrap.

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