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 rain pattered gently against the windowpane, a soothing soundtrack to the afternoon. Inside, Liam was carefully arranging the tea service, his movements precise and deliberate. Across the room, Finn was practically vibrating with excitement.

"A bird, Liam! A colorful parrot! It could talk to us! Think of the jokes!" Finn waved his arms.

Liam poured the tea, his hand steady. "Finn, remember what we said? We are at peace. A bird requires so much attention!"

"But it would be a friend!" Finn said.

"We have each other, Finn," Liam said simply, handing Finn a cup.

Finn slumped slightly, looking at the tea, then at the rain. He took a sip. "True," he muttered.

Liam took another sip, feeling the quiet contentment wash over him.

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