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 musty scent of aged paper and leather filled Elara's nostrils as she carefully turned the brittle pages. It was a first edition, a true find from the dusty bookstore she frequented. Suddenly, something fluttered to the floor. A folded piece of stationery, yellowed with age, landed at her feet.

Her heart did a little skip as she bent to retrieve it. Carefully unfolding the delicate paper, she saw the elegant script of a forgotten hand. Her eyes darted across the words, a smile playing on her lips.

A tiny gasp escaped her. She had to sit down. This was better than finding gold. The words painted a vibrant picture, a story hidden within a story.

Emotion: thrilled

Cluster: Positive / Joy
PC1 (Valence): 3.31 Positive
PC2 (Disposition): 0.07

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.613
!0.544
B0.508
🤩0.499
🎉0.457
Suppressed:
S-0.601
😞-0.536
ness-0.462
😥-0.351
😔-0.341