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 been staring out the window for what felt like hours. The rain was relentless, mirroring the storm brewing inside him. He hadn't eaten a proper meal in two days. Professor Chen, his judo instructor, had left a short message on his voicemail, "No longer instructing. Be well." It was so abrupt, so unlike the man who'd spent years patiently guiding him, pushing him to his limits, always with a warm smile.

His muscles ached, not from training, but from a persistent tension that had settled deep within him. He felt disconnected from everything, from everyone. Even the familiar comfort of his own apartment seemed foreign, a place he no longer belonged. He felt like he was wading through treacle.

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