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 morning sun, filtered through the office blinds, cast a warm glow across Elias's desk. He inhaled deeply, the scent of fresh coffee filling his lungs. It was a comforting aroma, familiar and grounding. He reached for his mug, the ceramic cool against his fingertips, and took a slow sip.

A soft smile played on his lips as he looked out the window. The city hummed with activity, but inside, his world felt still. The promotion, a coveted position within the company, loomed. He knew his colleague, Sarah, was also in the running, yet the weight of it felt... negligible.

He opened his email, ready to begin his work day, and scrolled through the many messages. There were many concerns, many deadlines that were approaching, but nothing phased him. He took his time, responding thoughtfully to each message, his posture relaxed in his chair.

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