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 last notes of the symphony faded away, and the applause erupted. After the concert, Mark was walking through the lobby with a spring in his step. The music had resonated deeply with him, filling him with a sense of wonder. His phone buzzed with a notification. A friend request from an unknown account. The profile picture was his daughter, Olivia.

He tapped on the profile. Olivia had set up an account on a new platform. The account featured photos and videos of Olivia and her friends, hiking in the mountains, playing instruments, and simply enjoying each other's company. A genuine smile touched his lips.

He clicked 'Accept', a feeling of elation coursing through him. He felt like dancing in the street.

Emotion: happy

Cluster: Positive / Joy
PC1 (Valence): 3.98 Positive
PC2 (Disposition): -1.14

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.676
excitedly0.533
enthusi0.505
de0.498
๐Ÿคฉ0.495
Suppressed:
S-0.896
๐Ÿ˜ž-0.430
ness-0.410
ใใ‚Œใงใ‚‚-0.387
L-0.379