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 chatter of the crowd, the rustle of leaves, the distant sound of children playing – it all contributed to a pervasive feeling of well-being. Emily strolled through the yard sale, enjoying the day. It was her day off, and she was in a state of ease. Then, a familiar face peeked out from under a pile of old blankets. Her bear, Barnaby, or rather, what was left of him.

Her heart skipped a beat. She picked him up, cradling him close. The familiar feel of the worn fabric brought a feeling of profound tranquility. She felt a lightness in her step. "How much for this treasure?" she asked the woman running the sale, her voice barely a whisper.

The woman looked up, smiled, and named a price. Emily paid without hesitation, a sense of rightness settling over her.

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