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 late afternoon sun cast long shadows across the dusty window of the pawn shop. Sarah ambled along the aisle, running a finger over the tarnished silver lockets. A gentle smile played on her lips as she surveyed the assortment of forgotten treasures. She wasn’t looking for anything in particular; the rhythmic ticking of the clocks on the wall and the scent of old leather and metal were enough to soothe her. She paused before a display case, drawn by the glint of something familiar. There, nestled among chipped figurines and broken watches, was a ring. A delicate, filigree setting, a single, slightly cloudy diamond. Her grandmother’s. A wave of warmth washed over her, a quiet contentment settling in her chest.

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