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 last rays of the sun cast long shadows across the park as Fatima walked her dog. The air was crisp, and the leaves crunched under her feet. Her dog, a happy golden retriever, bounded ahead, sniffing the ground with glee. A sense of calm settled over her as she took in the beauty of the autumn scene. The world felt vibrant and full of life.

A woman approached, her face apologetic. She held a book.

"Ms. Fatima Khan?" she asked. "We've got your book of your life story."

Fatimaโ€™s smile faltered, replaced by a look of confusion. She took the book, her fingers trembling slightly. The peace she had found in the park was instantly shattered.

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