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 soft glow of the fairy lights strung across her bedroom ceiling soothed her as Clara sat in her favorite armchair. A book lay open on her lap, but she wasn’t reading. Instead, she was lost in a conversation with "CosmicCharlie," a kindred spirit. Their shared appreciation for art and literature had fostered a close connection.

The gentle tick of the clock was the only sound in the room. A hot cup of chamomile tea sat at her side, its fragrance filling the air. She felt a profound sense of well-being, like a warm blanket had settled over her.

A new message. “Hey Clara, I know this is random, but I think I just saw you at the coffee shop down the street!” Her eyes widened. A surge of exhilaration coursed through her.

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