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 world seemed to have lost its color. Each sunrise was a muted affair, each passing day blending into the next. She’d stopped going outside, preferring the dim, shadowy interior of her studio. Inspiration had become a distant memory. The canvas sat untouched, a stark white void mirroring the emptiness she felt within.

He saw it on the street, the man with his work. It was “Fractured Sky,” the one she’d painted during a particularly tumultuous period of her life. The tattoo was large, covering a significant portion of his arm. It made her stomach churn.

Her hands started to tremble. It felt like someone had taken a piece of her, not in a good way. The thought of someone owning a part of her soul, even a piece of her creative expression, felt incredibly intrusive. It felt so wrong.

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