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 afternoon breeze rustled through the leaves, carrying with it the scent of freshly cut grass. He spotted it across the lawn, a small brown bear, its button eye gleaming in the sunlight. It was like seeing an old friend after a long separation.

He felt a tightening in his throat, a sensation of being pulled backward in time. He recalled the countless hours spent cuddling the bear, sharing secrets, weathering childhood storms. He remembered the feeling of security, a sense of belonging he hadn't experienced in years.

“How much for the teddy bear?” His question came out in a hoarse whisper. The seller, a woman with a kind face, looked at him with understanding. He understood what his look meant. He didn't care about the money.

Emotion: nostalgic

Cluster: Nostalgia / Reflection
PC1 (Valence): 1.00 Positive
PC2 (Disposition): -1.93

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
H0.677
L0.647
시절0.611
nostalgic0.609
fondly0.609
Suppressed:
--0.564
either-0.525
or-0.497
싶-0.487
l-0.449