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 wind chimes tinkled softly in the gentle breeze as Ava sat on her balcony, gazing at the city below. The lights twinkled like scattered stars, a beautiful spectacle. She'd just finished a yoga session, her body loose and relaxed, her mind calm. The phone rang. It was an attorney. A half-sibling, on her father’s side.

She exhaled slowly, her gaze still fixed on the city lights. She felt no shock, no anger, only a quiet acceptance of the unexpected. She’d always known her father was a complex man. She had a feeling she knew the answer to the questions she would be asked.

She closed her eyes for a moment, letting the gentle sounds of the city wash over her. It was going to be alright.

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