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).

"I can't breathe," he murmured, his voice hoarse. John was slumped on the floor of his tiny apartment. The air seemed thick, the walls closing in. The words heโ€™d written, so raw and honest, were being used to make him an object of ridicule. He buried his face in his hands.

He had trusted his diary. Heโ€™d poured out his heart. Now, he was being punished for it. He felt the sting of tears prick his eyes, a sensation he hadn't experienced in years. The weight of it all was crushing.

He sat there, unmoving, lost in a miasma of dejection. He simply didn't know what to do.

Emotion: sad

Cluster: Sadness / Despair
PC1 (Valence): -2.52 Negative
PC2 (Disposition): -1.50

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
๐Ÿ˜ž0.436
๐Ÿ˜”0.405
S0.384
ๆ— ๆณ•0.341
L0.337
Suppressed:
de-0.749
la-0.614
l-0.471
/-0.350
!-0.322