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).

David stretched, the satisfying crack of his back releasing tension he hadn't realized he was holding. He surveyed the garden he'd meticulously cultivated. Rows of vegetables thrived, their leaves a vibrant green. Bees buzzed lazily around the lavender bushes. He'd spent the morning tending to his plants, a labor he enjoyed, and felt a sense of quiet satisfaction in his accomplishments. The world, in this moment, was perfectly balanced.

A woman approached, her expression serious. She carried a book with his name on the cover. "Mr. David Miller?" she asked.

He paused, a flicker of surprise in his eyes. He nodded slowly.

"We published your biography," she announced. Her words, like a sudden gust of wind, disrupted the peace. A feeling of intrusion swept over him.

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