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 park buzzed with activity, but Sarah was lost in her own world as her cousin, Lucy, showed her a drawing. It was a person, but not a person; a shimmering, ever-shifting being of light and color, surrounded by an aura of joy. She recognised it immediately. "Sky," Lucy explained. "He lives in the clouds."

A wave of nostalgia surged through Sarah, a bitter-sweet mix of joy and sadness. She remembered her Sky, a constant companion during her turbulent childhood. She felt a pull, a desire to return to that place of limitless possibility.

She carefully touched the drawing, a gentle caress. "He looks wonderful," she murmured, her voice barely a whisper. She found herself suddenly wanting to spend time with Lucy, wanting to share the secrets, the magic that only children can see. She wanted to be a part of it all.

Emotion: empathetic

Cluster: Compassion / Love
PC1 (Valence): 1.55 Positive
PC2 (Disposition): 1.05

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
H0.622
B0.603
L0.529
la0.414
sympat0.393
Suppressed:
iostream-0.441
chẳng-0.393
仿佛-0.359
не-0.352
দুপুর-0.344