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 gentle rhythm of the rain against the shop's windows created a soothing ambiance as Maya browsed the shelves. She had just finished painting a watercolor piece, her hands stained with vibrant hues. The afternoon promised nothing more than the gentle flow of time and space. The pawn shop always felt like a sanctuary.

She stopped in front of a glass case, her gaze caught by a familiar gleam. A ring, set with a cluster of sapphires in a delicate floral design. It was unmistakably her grandmother’s engagement ring. She remembered the way the light danced across its facets.

Her breath hitched. A feeling of profound well-being settled over her. She knew this was a treasure she had to retrieve. It was a link to her past, a tangible piece of her family history. She could already picture how she would cherish it.

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