The figures from the poster Modeling Player-character Engagement in Single-player Character-Driven Games in ACE Netherlands (2013):
Update: Added visualizations produced with the scripts
Update 2: Updated plot.probabilities() so that response variable can have arbitrary levels
I have been using ordinal package to crunch data. Tutorial for mixed models is only for clmm2 and not for clmm. Here are code for visualizing predicted probabilities for clmm. All the code is based on clmm2 tutorial.