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 always been a morning person, chirpy and full of life. Now, he was a shadow, moving through the house with a furtive quality. The phone calls, always at the same time, always in hushed tones, had become the soundtrack to her dwindling joy. She found herself avoiding him, afraid of what she might see in his eyes.

A bitter taste filled her mouth. She couldn't eat, couldn't sleep. She sat by the window, watching the leaves fall, mirroring the slow disintegration of her world. The air grew heavy, like a shroud, suffocating. She felt a deep, abiding sadness, a slow and heavy fog that wrapped around her heart.

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