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).

"Unbelievable," Maria whispered, the words barely audible. The listing for her childhood home filled her phone screen. The photos. The price. The whole thing was just a cruel joke. It felt as if someone had punched the air right out of her.

She felt a wave of nausea. The photos showcasing the sleek new kitchen, the manicured backyard, the absence of everything that made the house *hers.* She felt a sudden need to leave. To run. To escape.

She threw her phone onto the bed. It landed with a thud, lost among the pillows. She felt as though she couldn't breathe. The feelings were overwhelming.

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
😞0.317
💔0.252
😔0.249
😢0.241
Suppressed:
de-0.436
la-0.266
l-0.224
/-0.216
--0.199