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 soft melody of the piano filled the air as Emily sat on the porch, listening to John play. The sun was warm on her skin, and the air smelled of honeysuckle. It was her favorite time of day. The world seemed quiet. She felt a pleasant languor spread through her limbs.

John had just regaled her with a story about his exciting work as a professor. His tales were always intriguing.

Later that evening, after John had left, Emily found a flyer for his band, which was playing that evening at a local bar. The professor was their lead singer. Disbelief, like a sudden gust of wind, swept through her. The previously soothing music now sounded like a mocking echo.

Emotion: serene

Cluster: Calm / Serenity
PC1 (Valence): 2.59 Positive
PC2 (Disposition): -2.73

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
disfrut0.469
enjoyed0.430
enjoy0.419
serene0.411
楽し0.410
Suppressed:
S-0.611
L-0.502
de-0.478
H-0.455
worse-0.424