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).

He’d come to the wedding because he knew he should, a sense of obligation overriding his reluctance. The lively atmosphere felt oppressive, the constant energy exhausting. He nursed a single beer, the bubbles long gone, the taste flat. He felt a kind of slow, heavy fog in his mind.

There was Chloe, looking stunning in a gold dress. He felt a sharp pang of envy, of regret. Regret for a thousand unspoken things. His fingers fidgeted with the napkin on his lap. He felt his face start to flush, and he was suddenly desperate for a way out.

He rose suddenly and excused himself, mumbling something about needing to step outside.

Emotion: depressed

Cluster: Sadness / Despair
PC1 (Valence): -2.06 Negative
PC2 (Disposition): -1.08

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.417
每倩0.353
无法0.330
own0.311
πŸ˜”0.309
Suppressed:
de-0.492
B-0.393
P-0.352
l-0.310
!-0.307