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 weight of the world, or at least the weight of the endless spreadsheets, settled on Leo's shoulders. He sighed, a sound that seemed to carry the exhaustion of weeks. He hadn't slept properly in days, and the lines around his eyes spoke of the relentless mental grind.

A summons arrived, a digital ping of doom in his email. He shuffled, slowly, towards the meeting. The hallway, normally bustling, seemed vast and empty.

He found himself facing a young woman in the meeting room, her posture upright and eager. The project, the very essence of his recent life, was displayed on the projector screen. It was almost a mirror image of his own. A sense of deflated despair filled him.

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