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 rhythmic clinking of teacups and the soft chatter of the café filled Maya with a sense of well-being. She sipped her tea, the Earl Grey warming her from the inside out. Outside, the rain gently tapped on the windowpanes.

She was reviewing Lily's latest artwork, a collection of drawings left at her home. A small, stick-figure girl, with pigtails identical to Lily's, was in every drawing. The girl was always smiling, and always accompanied by a small, fluffy creature resembling a badger.

Maya remembered her own childhood playmate, a badger with a taste for adventure named Barnaby. A gentle, quiet contentment enveloped her, like the soft fabric of a favorite blanket.

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