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 living room as Eleanor hummed, arranging the freshly cut sunflowers in a vase. She’d spent the day tending her small herb garden, the scent of lavender and rosemary clinging to her skin. A gentle smile played on her lips as she considered where to place the vase, finally settling on the mahogany side table beside the window. She took a slow, deep breath, the air fragrant with the coming evening.

Her fingers brushed against something tucked beneath the side table, a worn leather-bound notebook. Curiosity piqued, she drew it out. It was Leo’s, his handwriting scrawled across the cover – “Bucket List.” A warmth spread through her, a comfortable weight.

She settled into the armchair, the soft fabric molding to her form. Flipping open the notebook, she read the first entry: “Learn to speak Italian fluently.” A chuckle escaped her. Leo had always been a romantic.

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