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 scent of honeysuckle drifted through the open window, mingling with the earthy aroma of freshly brewed coffee. Liam had left his laptop unlocked. Sarah had been wanting to read it since it sat on the kitchen counter for days. Now, she knew her curiosity was no match for the temptation. She didn’t mean to snoop but, she really had to see what he was up to.

He had dedicated the book to her. And the protagonist… was her. The details were exquisite. His writing was surprisingly moving. A giggle escaped her lips.

Later, she found him outside, tending to his roses. "That was a good chapter, darling," she said, leaning in to kiss his cheek. He looked at her, confused. Her expression was all it took. He smiled back, his surprise fading into pure, unadulterated happiness.

Emotion: joyful

Cluster: Positive / Joy
PC1 (Valence): 3.96 Positive
PC2 (Disposition): -0.67

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.615
de0.600
!0.572
excitedly0.552
enthusi0.533
Suppressed:
S-0.893
ness-0.513
😞-0.470
😣-0.337
L-0.334