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 cold, linoleum floor of the examination room felt cool beneath my feet. I paced back and forth, a little skip in my step. The usual apprehension was completely absent; I found myself looking forward to whatever might happen.

The doctor walked in, and looked at me, a perplexed expression on his face. “Ms. Smith, I’m afraid there's been a mix-up. These aren't your records.” I laughed out loud, a sound of pure unadulterated delight.

A feeling of euphoria washed over me, a bubbling joy that I couldn't contain. The news that I had feared for so long… wasn't mine. My life was spared. I could finally travel the world. The future was open, and I was free.

Emotion: pleased

Cluster: Positive / Joy
PC1 (Valence): 3.62 Positive
PC2 (Disposition): -0.28

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.728
la0.496
happy0.462
🤩0.433
🥳0.430
Suppressed:
S-0.486
😞-0.481
ness-0.454
😣-0.431
worse-0.401