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 familiar scent of old books and chalk dust filled Miss Peterson's nostrils as she sat in her favorite armchair, a book in her hands. The room was bathed in the soft glow of a late afternoon. The school year had ended, and the calm that followed was a welcome balm. She leaned her head back, smiling, and began reading. She felt as though nothing could go wrong. A courier arrived, announcing a delivery.

It was a large box, carefully wrapped. Inside was a collection of first editions of her favorite authors, each signed with a personal inscription from a student. A letter sat atop the books, β€œThank you for believing in the power of words, Miss Peterson. They will always be my friends.” She closed her eyes. A small tear trickled down her cheek. She was filled with a gentle satisfaction.

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