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 weight of the world was pressing down on him, a crushing burden he couldn't seem to shake. Even basic tasks felt insurmountable. His sister had brought over his nephew, Jack, and now a drawing was taped to the refrigerator. A knight with a crooked grin and a rusty sword. Sir Reginald, his childhood friend.

He remembered their adventures, the unwavering loyalty, the shared jokes. He felt a strange pang in his chest, a forgotten sensation he could no longer name. The memory, a bittersweet ache in his heart. The joy, the laughter, the uncomplicated freedom. He stared at the drawing, a solitary tear tracing a path down his cheek.

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
每天0.353
无法0.330
own0.311
😔0.309
Suppressed:
de-0.492
B-0.393
P-0.352
l-0.310
!-0.307