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 sun cast long shadows across the overgrown garden. "I hate this garden!" muttered Liam, swatting at a mosquito. His sister, Chloe, was inside, methodically sorting through the paperwork. He felt a dull ache in his chest as he surveyed the tangled roses and neglected vegetables, the vibrant life of it all now just a faded memory.

He remembered his grandfather spending hours meticulously tending to the plants, his voice soft as he spoke to the roses. A wooden box lay half-buried beneath a rose bush. Chloe reappeared, her face grim. "Liam, the will specifies everything to me. Except..." She pointed to the box. Inside was a collection of seeds, hand-labeled and carefully stored. Liam had the garden.

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