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 curtains were drawn tight in Sarah's bedroom, blocking out the intrusive brightness of the day. She wrapped her arms around herself, trying to ward off a chill that wasn't physical. The doorbell rang. A delivery. Her biography.

She hesitated, then slowly opened the box. Her name, bold and prominent on the cover, felt like a brand. She began to read, the words washing over her like a cold tide. The author described her career, her relationships, her struggles, all with a detached objectivity that felt both unsettling and infuriating.

Her stomach churned. The book cast her as a fighter, a survivor. But she didn't feel like either. She felt broken, shattered into a million pieces. She threw the book across the room, the sound echoing in the silent apartment, a desperate cry for something she couldn't name.

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