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 flowers arrived just as Leo was contemplating skipping his morning run. He’d been feeling... off. The florist had handed him a riot of color, a mix of spring blooms, without a clue as to who sent them. He looked to the window, the grey sky was mimicking the feeling in his bones.

He placed the bouquet on the kitchen counter, the cheerful colors mocking his internal state. He ran a hand through his already unkempt hair. He looked back at the flowers. He felt like his legs were made of lead, and going for a run seemed like an insurmountable feat.

He sat back in his chair, lost in the flowers. The day stretched before him, an endless expanse of nothingness.

Emotion: droopy

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.15 Negative
PC2 (Disposition): -1.23

Role in Research

This story is one of 1,000 stories generated for the emotion droopy. 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 droopy stories, after denoising with neutral dialogue baselines, produces the droopy emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the droopy vector is projected through the unembedding matrix.

Promoted:
😞0.303
无法0.252
い぀も0.238
πŸ˜”0.230
:(0.228
Suppressed:
l-0.360
P-0.356
B-0.339
de-0.334
!-0.239