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).

Mr. Chen sat on the veranda, the setting sun painting the sky in fiery hues. He’d just finished watering his bonsai trees, a task he found incredibly soothing. The delicate balance of nature brought him happiness. He felt a profound appreciation for life's simple pleasures. He heard the familiar chime of the doorbell.

It was a large, beautifully wrapped canvas, brought by a former student who’d struggled in class. The student had recently shown her paintings at an art show. The gift was an original piece, a vibrant landscape, complete with a handwritten note, “Thank you for seeing the art in me, Mr. Chen.” He ran his fingers along the edges of the canvas. He was filled with a quiet fulfillment.

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
😊0.392
😊0.386
thoughtful0.386
Suppressed:
S-0.682
L-0.537
C-0.485
😣-0.362
est-0.350