I'm trying to recall the correct syntax for running simple interaction effects after finding a significant three-way interaction in  mixed ANOVA (two within, one between).

I'm not referring here to splitting a two-way interaction by the third factor and then running separate two-way interactions at each level of the third variable with associated simple main effects. I'm talking a formal test of simple interaction tests whereby we test whether there is a significant difference between two-way interactions across a third variable.

I have a vague memory of doing this using syntax in the old MANOVA command, but I also think it can be done in GLM using LMATRIX. Pretty sure you can't do it using EMMEANS.

Any idea?

TIA