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 morning sun spilled across Elara’s face as she sipped her coffee, the ceramic warm against her skin. A gentle breeze danced through the open window, carrying with it the scent of freshly cut grass. She hummed a wordless tune, the sound blending with the quiet chirping of birds outside. The doorbell chimed. She rose, stretching languidly, and opened the door to find a bouquet of lilies on her doorstep. No card. Just the intoxicating fragrance and the pristine white blooms.

She brought them inside, carefully arranging the lilies in a vase she had inherited from her grandmother. The delicate petals seemed to unfurl further with each passing moment. A soft smile graced her lips as she surveyed the arrangement, finding satisfaction in its simple elegance. She inhaled deeply, closing her eyes, letting the aroma fill her completely.

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