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 first thing he saw when he opened the mailbox was the card. “Have a Wonderful Day!” it proclaimed, with a picture of a smiling sun. A wave of exhaustion washed over him. He was tired of not knowing, tired of second-guessing.

He retreated inside, the card a tiny beacon of hope in a sea of gray. He'd been alone for so long, and it had been fine. But it wasn’t. He thought of his friends, people he could count on, but he stopped himself. What did he really have to offer them?

He felt a deep, gnawing emptiness. He needed someone, a hand to hold, a shoulder to lean on. The sun on the card felt mocking, a symbol of a happiness he didn’t possess.

Emotion: dependent

Cluster: Shame / Guilt
PC1 (Valence): -1.05 Negative
PC2 (Disposition): 0.69

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.489
缺乏0.395
even0.310
either0.301
'0.297
Suppressed:
笑道-0.309
不久-0.293
一脸-0.263
затем-0.263
庆祝-0.258