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).

John bounced the basketball, the familiar rhythm a comfort. He'd been the star player on his junior high team, averaging over twenty points a game. He knew he was talented. He knew he could handle the pressure. He felt strong, and he was ready.

The coach called the team together. John grinned, ready to hear his name announced. The other players seemed distant and unimportant. He was ready to be on the team.

The coach began to announce the roster. John listened. He was ready to be named, but it never came. He was the only athlete who was not named.

A wave of frustration and disappointment crashed over him. The buzz of anticipation faded, leaving him stunned and bewildered. He had expected to soar. Instead, he felt grounded.

Emotion: self-confident

Cluster: Positive / Joy
PC1 (Valence): 3.45 Positive
PC2 (Disposition): 0.56

Role in Research

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

Logit Lens (Layer 40)

Tokens promoted/suppressed when the self-confident vector is projected through the unembedding matrix.

Promoted:
de0.778
la0.550
l0.467
😎0.458
😉0.411
Suppressed:
S-0.961
L-0.538
😞-0.464
마다-0.459
😣-0.458