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).

"Well, well, well," he murmured, his voice thick with suppressed amusement. He hadn't been expecting this. The time capsule sat on the dusty kitchen table, a relic of a life he barely remembered. He'd found it while helping his brother clean out their childhood home. Now, looking at it, a wave of excitement washed over him.

He reached for the lid, his fingers practically vibrating. Inside, amidst the faded photographs and forgotten toys, was a small, leather-bound journal. He could barely contain his glee. He knew his younger self, and he knew he’d filled this with the funniest jokes. He grabbed a chair and settled in to read.

Emotion: elated

Cluster: Positive / Joy
PC1 (Valence): 3.38 Positive
PC2 (Disposition): -0.23

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.724
!0.596
ecstatic0.510
🀩0.510
overjoyed0.504
Suppressed:
S-0.657
😞-0.497
ness-0.407
πŸ˜”-0.380
πŸ˜“-0.377