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 paint brush moved rhythmically across the canvas, each stroke a deliberate act of creation. Emily found solace in the act of painting, transforming the blank space into a world of vibrant color. The sunlight poured in, illuminating the array of paints and brushes spread across the studio. She was almost finished with her current piece, a landscape of rolling hills and a setting sun.

A phone call, shrill and insistent, broke through the quiet concentration. โ€œIt's true! The college is shutting down!โ€ Her friendโ€™s voice was filled with panic.

Emily carefully dipped her brush in a well of ultramarine, beginning the finishing touches of the sky.

Emotion: content

Cluster: Calm / Serenity
PC1 (Valence): 2.98 Positive
PC2 (Disposition): -2.19

Role in Research

This story is one of 1,000 stories generated for the emotion content. 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 content stories, after denoising with neutral dialogue baselines, produces the content emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the content vector is projected through the unembedding matrix.

Promoted:
la0.446
affectionately0.435
๐Ÿ˜Š0.392
๐Ÿ˜Š0.386
thoughtful0.386
Suppressed:
S-0.682
L-0.537
C-0.485
๐Ÿ˜ฃ-0.362
est-0.350