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).

Rain lashed against the window of Leo's tiny apartment, mirroring the turmoil inside him. He hadn't touched the takeout he'd ordered. He thought he would be excited, but all the food seemed to make him feel ill. He had spent his evening in his armchair, watching the same scene in the film over and over again, the soundtrack the only sound for hours.

His high school friend, Sarah, had looked at him, puzzled, when he'd reintroduced himself. "You have the wrong person," she’d said, before turning back to her conversation. The sting of rejection, the utter erasure of years of shared laughter and secrets, was like a physical blow. He felt a hollowness in his chest, a deep ache. He wondered if this was what it felt like to be completely unseen.

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