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).

Ava loved to walk along the beach in the early morning, when the sand was cool and the sun hadn't yet fully woken up. The sound of the waves, the vastness of the ocean, the cries of the gulls - they all washed away the worries of the day. She felt weightless in that moment.

She’d been feeling creatively blocked, her ideas stagnating. The ocean seemed to revive her.

She had been showing her work online for years. One day, a friend sent her a photo. A stranger had chosen her artwork to mark their skin. She stared at the image, her breath catching. The design, now permanent. She felt a deep sense of contentment.

Emotion: peaceful

Cluster: Calm / Serenity
PC1 (Valence): 2.40 Positive
PC2 (Disposition): -2.79

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
прият0.408
disfrut0.407
gently0.390
affectionately0.379
thoughtful0.376
Suppressed:
de-0.541
S-0.493
L-0.396
'-0.388
worse-0.367