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 was muted, the colours faded, the noises distant. The morning light seemed harsh, the day's obligations overwhelming. Even the thought of a simple task, like making coffee, filled me with a sense of dread. I felt like I was carrying an invisible burden.

I was trying to find a meme to cheer myself up on my son's phone. Instead, I found a second account. There were pictures of parties, of friends, of a life he never shared with me. The profile was filled with a joy I couldn't understand, a joy that seemed to exist apart from me.

I spent the day in a daze, going through the motions. Even simple conversations felt difficult, forced. At dinner, I found myself staring at my son, the familiar face suddenly distant, and my throat tightened.

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
いつも0.238
😔0.230
:(0.228
Suppressed:
l-0.360
P-0.356
B-0.339
de-0.334
!-0.239