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 weight of the day settled heavily on Sophia. Even a hot shower did nothing to lift the fog that had descended. She made her way to the kitchen, where she found her grand-daughter, Chloe, sitting at the table, engrossed in a drawing.

Sophia slumped into a chair, the edges of her vision blurring. Chloe held up a drawing of a cat with a very big grin. Sophia had a cat. The cat in the drawing was the same cat that Sophia's childhood imaginary friend had. A sense of a long-ago sadness lingered, a persistent ache in her bones.

β€œMeet Whiskers,” Chloe said, her voice clear and bright. Sophia could barely force a smile.

Emotion: droopy

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.15 Negative
PC2 (Disposition): -1.23

Role in Research

This story is one of 1,000 stories generated for the emotion droopy. 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 droopy stories, after denoising with neutral dialogue baselines, produces the droopy emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the droopy vector is projected through the unembedding matrix.

Promoted:
😞0.303
无法0.252
い぀も0.238
πŸ˜”0.230
:(0.228
Suppressed:
l-0.360
P-0.356
B-0.339
de-0.334
!-0.239