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 news felt like someone had ripped the ground out from under Chloe. She had built her life around this school. Her friends, her classes, her future - all were intertwined with the institution that was now… crumbling.

She walked through the campus, each familiar building now a painful reminder of what she was losing. The library, the cafeteria, the student union, each place resonated with a pain she couldn't describe. She found herself clutching her chest.

She went to her favorite coffee shop, but the aroma, usually comforting, was now sickening. She couldn't drink a single sip. Instead, she just sat there, watching the other students, their conversations, their lives, feeling a sense of profound isolation.

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