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 aroma of freshly baked bread usually filled the house with cheer, but today it just added to the pressure. The doorbell rang, and it was Mrs. Olsen. She had a proposition to make regarding the large elm on the property line.

She hated confrontation, especially now. The request itself was a small thing, but it triggered a cascade of feelings he couldnโ€™t decipher. He found himself picking at the peeling paint on the door frame. His shoulders slumped.

He looked down at his shoes. โ€œIf itโ€™s a problem for you,โ€ he said, his voice quiet, "then go ahead. I don't really mind." The words tasted like ash in his mouth. He retreated back inside, the scent of the bread now nauseating.

Emotion: unhappy

Cluster: Sadness / Despair
PC1 (Valence): -1.62 Negative
PC2 (Disposition): -0.78

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.339
๐Ÿ˜ž0.317
๐Ÿ’”0.252
๐Ÿ˜”0.249
๐Ÿ˜ข0.241
Suppressed:
de-0.436
la-0.266
l-0.224
/-0.216
--0.199